© 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. 73542
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    _begin
    -0.07
    open
    -0.07
    Ј
    -0.07
     negoci
    -0.07
    rending
    -0.06
    receive
    -0.06
    outer
    -0.06
    /open
    -0.06
    lemetry
    -0.06
     Publisher
    -0.06
    POSITIVE LOGITS
    而这
    0.09
    风筝
    0.07
    (wp
    0.07
    charm
    0.07
    商
    0.07
    恍
    0.07
    ัน
    0.07
     hob
    0.07
    工
    0.07
    嘲笑
    0.07
    Activations Density 0.634%

    No Known Activations