© 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. 108535
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    éĩijåŃĹå¡Ķ
    -0.33
    ~↵↵
    -0.30
    peak
    -0.25
    (rc
    -0.25
    staw
    -0.24
    å¯ĦãģĽ
    -0.24
    ائÙĦ
    -0.24
     sucesso
    -0.23
    pir
    -0.23
    _RGB
    -0.23
    POSITIVE LOGITS
    个åĪ«
    0.33
    leshoot
    0.28
     Holmes
    0.27
    ä¸Ģ页
    0.26
    æ¦ľ
    0.26
    æĪij说
    0.26
    bies
    0.26
    çĹķ
    0.26
    lies
    0.25
    ’S
    0.25
    Activations Density 9.638%

    No Known Activations

    This feature has no known activations.