© 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. 88638
    Prev
    Next
    INDEX
    Explanations

    code, documentation, programming

    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
    iggins
    -0.30
    upid
    -0.29
    忸
    -0.27
    Ļ¶
    -0.26
    ieÅĦ
    -0.26
    iber
    -0.24
     lig
    -0.24
    uchos
    -0.24
    quine
    -0.24
    ·æĸ°
    -0.23
    POSITIVE LOGITS
    欢è¿İ
    0.29
    ç»ĦåIJĪ
    0.27
    (sv
    0.27
    å¥ĩå¦Ļ
    0.26
    =R
    0.26
    ä¹Łåı¯ä»¥
    0.26
    |R
    0.26
    头
    0.25
     Creed
    0.25
    onal
    0.25
    Activations Density 0.008%

    No Known Activations