© 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. 11-RESID-POST-AA
    11. 2247
    Prev
    Next
    INDEX
    Explanations

    economic impact

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     incompetence
    -0.07
    .GO
    -0.07
     complained
    -0.07
     SA
    -0.06
     lag
    -0.06
     Airways
    -0.06
    ่อง
    -0.06
    issippi
    -0.06
    kas
    -0.06
     ago
    -0.06
    POSITIVE LOGITS
    /result
    0.07
     없습니다
    0.07
     narration
    0.07
    _chance
    0.07
    IPLE
    0.06
    設備
    0.06
    蜇
    0.06
     Cougar
    0.06
    EDURE
    0.06
    (sl
    0.06
    Activations Density 0.026%

    No Known Activations