© 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. 140919
    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
    Not in Any Lists

    No Comments

    Negative Logits
    æ¼ı
    -0.29
    éĿĴæĺ¥
    -0.26
    è´¢
    -0.26
    égorie
    -0.25
     pal
    -0.25
    èĨ³
    -0.24
    naissance
    -0.24
     consulted
    -0.24
    ãĥģãĥ£ãĥ³
    -0.23
    ç¼ĸ
    -0.23
    POSITIVE LOGITS
     Dunk
    0.28
    ä¸įåħį
    0.27
    æĹłæķĮ
    0.27
     Kaiser
    0.26
    åĴ«
    0.25
     subs
    0.25
     ///</
    0.25
    andex
    0.25
    ︱
    0.24
    avad
    0.24
    Activations Density 5.445%

    No Known Activations

    This feature has no known activations.