© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 128814
    Prev
    Next
    INDEX
    Explanations

    Questions and answers

    np_max-act · gemini-2.0-flash

    Q&A-style forum formatting and first-person problem statements, especially in workplace/academic contexts.

    oai_token-act-pair · gpt-5Triggered by @vetterc0

    first-person advice-seeking questions about handling problems, especially framed with direct interrogatives.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     desk
    -0.07
    企图
    -0.07
     lanz
    -0.06
    azure
    -0.06
    』
    -0.06
    вшись
    -0.06
    _LOOKUP
    -0.06
    解说
    -0.06
    Australian
    -0.06
     pourquoi
    -0.06
    POSITIVE LOGITS
     עבודת
    0.07
     עובדים
    0.07
     Kohana
    0.07
    ++){
↵
    0.07
    治疗方法
    0.07
    argin
    0.07
     وقت
    0.07
    .loader
    0.07
    结局
    0.07
    /socket
    0.07
    Activations Density 0.059%

    No Known Activations