© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 107424
    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
    çIJ¶
    -0.28
     ded
    -0.28
    preh
    -0.27
    é¦ĸ
    -0.27
    å¾ĹäºĨ
    -0.25
    ophile
    -0.25
    iterate
    -0.25
    eton
    -0.24
     headings
    -0.24
    (OP
    -0.24
    POSITIVE LOGITS
     PROP
    0.26
    æ§İ
    0.26
    [js
    0.26
    -spinner
    0.25
    æĿ¡ä»¶ä¸ĭ
    0.24
    uchi
    0.24
    ropp
    0.23
    ä¸ŃåĽ½ç»ıæµİ
    0.23
    æĹ¥æĻļéĹ´
    0.23
     counsel
    0.23
    Activations Density 8.361%

    No Known Activations

    This feature has no known activations.