© 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. 63510
    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
    ç¬ı
    -0.29
    edelta
    -0.27
    opl
    -0.27
    éĹ¾
    -0.26
    ut
    -0.26
     ut
    -0.26
    çĽ¾
    -0.25
    urb
    -0.25
    pir
    -0.25
    èĤļ
    -0.24
    POSITIVE LOGITS
    ãĥ¼ãĤ·ãĥ§ãĥ³
    0.25
    quee
    0.25
     creeping
    0.24
    çŃĩ
    0.24
    ä¸ĢåŃĹ
    0.24
    imary
    0.24
    éħ¡
    0.24
    建åħļ
    0.23
    yw
    0.23
    大åĵ¥
    0.23
    Activations Density 4.998%

    No Known Activations

    This feature has no known activations.