© 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. 107009
    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
    åĭī
    -0.30
    èµ°åĩºæĿ¥
    -0.28
    .Quantity
    -0.27
    æŁ¥çľĭæĽ´å¤ļ
    -0.25
    è¾ĺ
    -0.25
    ORIES
    -0.25
    OG
    -0.24
     Lot
    -0.24
     Cree
    -0.24
    иж
    -0.24
    POSITIVE LOGITS
    éķ¿æľŁ
    0.29
    è¯Ħ级
    0.26
    à¹ģà¸ŀ
    0.25
     Braz
    0.24
     irrig
    0.24
    LETTE
    0.24
    çļĦç«ŀäºī
    0.24
    vore
    0.23
    ç¾Ł
    0.23
    enne
    0.23
    Activations Density 14.874%

    No Known Activations

    This feature has no known activations.