© 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. 142148
    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
    æĤļ
    -0.31
    é£İ鼨
    -0.28
    lectric
    -0.28
     Dodd
    -0.26
     FEMA
    -0.26
     unsafe
    -0.25
    ä¿ĿçķĻ
    -0.25
    ogie
    -0.24
    ubbo
    -0.24
    Hex
    -0.24
    POSITIVE LOGITS
    æĹıèĩªæ²»åİ¿
    0.28
    èħ´
    0.28
    [__
    0.26
     {{--<
    0.25
     wann
    0.25
    åį¬
    0.24
    转身
    0.24
    ',{'
    0.24
    andan
    0.23
    è·Łä½ł
    0.23
    Activations Density 28.813%

    No Known Activations

    This feature has no known activations.