© 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. 142246
    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
    quiv
    -0.30
    åĬŀçIJĨ
    -0.26
    import
    -0.25
    械
    -0.24
    åĽ¢éķ¿
    -0.24
     vy
    -0.24
    份é¢Ŀ
    -0.24
    ys
    -0.24
     import
    -0.23
    lems
    -0.23
    POSITIVE LOGITS
    -working
    0.25
     AVC
    0.25
    PTY
    0.24
    gien
    0.24
    :init
    0.24
    &C
    0.24
    (Activity
    0.23
    :Array
    0.23
     guilty
    0.23
    pch
    0.23
    Activations Density 9.231%

    No Known Activations

    This feature has no known activations.