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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 82107
    Prev
    Next
    INDEX
    Explanations

    able

    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_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
     Attack
    -0.08
     setPosition
    -0.07
    数十
    -0.07
    担任
    -0.07
    サロン
    -0.07
    calloc
    -0.07
    Init
    -0.07
     שתי
    -0.07
    Joined
    -0.07
    辈
    -0.07
    POSITIVE LOGITS
    able
    0.09
    ables
    0.08
     readability
    0.07
    ible
    0.07
     measurable
    0.07
    服务能力
    0.07
    กร
    0.07
     Globe
    0.07
     Iterable
    0.06
    ɰ
    0.06
    Activations Density 0.122%

    No Known Activations