© 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. 25383
    Prev
    Next
    INDEX
    Explanations

    B

    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
     foreclosure
    -0.07
     redis
    -0.07
    试点
    -0.07
    .prompt
    -0.07
    著作權
    -0.07
     tangible
    -0.07
    .toList
    -0.06
    .MiddleRight
    -0.06
    创新型
    -0.06
    怆
    -0.06
    POSITIVE LOGITS
    AYOUT
    0.07
     sit
    0.07
    ość
    0.07
    ethod
    0.07
    AMILY
    0.07
    ème
    0.07
     cabe
    0.06
    .compat
    0.06
     =&
    0.06
    最多
    0.06
    Activations Density 0.015%

    No Known Activations