© 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. 19-RESID-POST-AA
    11. 70477
    Prev
    Next
    INDEX
    Explanations

    firearms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ":↵↵
    -0.07
    时效
    -0.07
    寞
    -0.07
    实行
    -0.07
    Ш
    -0.07
    分からない
    -0.06
    lettes
    -0.06
    办法
    -0.06
    得了
    -0.06
    收費
    -0.06
    POSITIVE LOGITS
     Andreas
    0.08
    Fmt
    0.07
    انخفاض
    0.07
     tsl
    0.07
    JP
    0.07
     hands
    0.06
    ThreadId
    0.06
     etiqu
    0.06
    py
    0.06
     LPARAM
    0.06
    Activations Density 0.037%

    No Known Activations