© 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. 140766
    Prev
    Next
    INDEX
    Explanations

    botox

    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
    inet
    -0.31
    ini
    -0.31
    rop
    -0.30
    iny
    -0.29
     rev
    -0.28
    ine
    -0.28
    imb
    -0.27
    éĢĨ
    -0.27
    pat
    -0.26
    æ³Ħ
    -0.26
    POSITIVE LOGITS
     ZERO
    0.27
     "[%
    0.26
    ()(
    0.26
     вÑĭз
    0.26
    ä¸ĭ车
    0.26
    /OR
    0.26
    oris
    0.25
    ترجÙħ
    0.25
    ä¸Ģ对ä¸Ģ
    0.24
    IFn
    0.24
    Activations Density 3.597%

    No Known Activations