© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 87092
    Prev
    Next
    INDEX
    Explanations

    Nag

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    -0.40
    æ°´éĿ¢
    -0.28
    sus
    -0.26
    ä¸įè¦ģ太
    -0.26
    cope
    -0.25
    åħij
    -0.25
    æł¹æį®ä¸įåIJĮ
    -0.25
    è·¤
    -0.25
    sheets
    -0.24
    éļıæīĭ
    -0.24
    POSITIVE LOGITS
    åįŁ
    0.24
    ework
    0.23
    Hôtel
    0.23
    ãģĹãģĭãģªãģĦ
    0.23
    ẩn
    0.23
     Rencontres
    0.22
    çļĦä¸Ģ项
    0.22
     blackmail
    0.22
     вÑĭпÑĥÑģк
    0.22
    rapy
    0.22
    Activations Density 0.141%

    No Known Activations