© 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. 20-TRANSCODER-HP
    7. 108560
    Prev
    Next
    INDEX
    Explanations

    dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    zte
    -0.28
    ://${
    -0.27
    å±ı
    -0.26
    åijķ
    -0.25
     designs
    -0.25
    estre
    -0.25
    wor
    -0.24
    æ¸´æľĽ
    -0.24
    zp
    -0.24
    spath
    -0.23
    POSITIVE LOGITS
     tip
    0.25
     etc
    0.25
     crank
    0.24
    Under
    0.23
     Lac
    0.23
     §§
    0.23
     iterating
    0.23
    头
    0.23
    ç«ĭæ¡Ī
    0.22
    gebung
    0.22
    Activations Density 2.919%

    No Known Activations