© 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 EvalsExportsAPI 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. 7-RESID-POST-AA
    11. 8714
    Prev
    Next
    INDEX
    Explanations

    ism

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rying
    -0.08
     coded
    -0.07
    眼中
    -0.07
    ->{
    -0.07
     pars
    -0.07
    ҥ
    -0.07
    مف
    -0.07
    聊
    -0.07
     forward
    -0.07
    执行
    -0.07
    POSITIVE LOGITS
    .toolStripSeparator
    0.07
     educators
    0.07
     Religion
    0.07
     Derm
    0.07
     раств
    0.07
    .csv
    0.07
     Salmon
    0.07
    Issuer
    0.07
     listings
    0.07
    ♏
    0.07
    Activations Density 0.016%

    No Known Activations