© 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. 111053
    Prev
    Next
    INDEX
    Explanations

    Research, studies, or attempts

    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
    Negative Logits
    éĿ¢
    -0.32
    ç¿ĺ
    -0.28
     Replies
    -0.27
    å¾Ĺä½ı
    -0.25
    uded
    -0.25
    LECTION
    -0.24
    ampp
    -0.23
    åĮĸè¿Ľç¨ĭ
    -0.23
    èĮĥ
    -0.23
    berger
    -0.23
    POSITIVE LOGITS
    prus
    0.26
     Trouble
    0.26
    มà¸Ļ
    0.25
    大å±Ģ
    0.24
    elah
    0.23
    ÙĪÙĨÙĬ
    0.23
    èĸ®
    0.23
    SID
    0.23
    åĩºçİ°éĹ®é¢ĺ
    0.23
    大ãģįãģĦ
    0.23
    Activations Density 0.084%

    No Known Activations