© 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. 108153
    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
    觸
    -0.28
    触
    -0.28
    ='${
    -0.26
     rs
    -0.26
    çľĭçĤ¹
    -0.24
    çİij
    -0.24
    æĿ¥çľĭ
    -0.24
    /WebAPI
    -0.24
     touch
    -0.24
    oubted
    -0.23
    POSITIVE LOGITS
    æĵį
    0.29
    ReturnType
    0.25
     slipped
    0.25
     maur
    0.25
    .observable
    0.24
     tav
    0.24
    -double
    0.24
    ä¼łæĿ¥
    0.24
    wick
    0.24
    OTA
    0.24
    Activations Density 8.808%

    No Known Activations

    This feature has no known activations.