© 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. 62992
    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
    å¤ļå¹´æĿ¥
    -0.30
    åģļ个
    -0.28
     novel
    -0.26
    apid
    -0.25
     Dirk
    -0.25
     cand
    -0.25
     novels
    -0.25
    olith
    -0.24
    getAs
    -0.24
    -before
    -0.24
    POSITIVE LOGITS
    arse
    0.29
    ora
    0.27
    æĬµæĮ¡
    0.25
    woods
    0.25
    essenger
    0.24
    人å±ħçݯå¢ĥ
    0.24
    iline
    0.24
    avana
    0.24
    ä¹°åĪ°
    0.24
    oran
    0.23
    Activations Density 0.158%

    No Known Activations

    This feature has no known activations.