© 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. 30-TRANSCODER-HP
    7. 96203
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ymous
    -0.26
    åįķ纯çļĦ
    -0.26
    /************************
    -0.24
    uge
    -0.24
    uges
    -0.24
    广
    -0.24
    feb
    -0.23
    udad
    -0.23
    peg
    -0.23
    ledge
    -0.23
    POSITIVE LOGITS
    èĺĸ
    0.26
    ç¢į
    0.25
    .setAuto
    0.25
    ç¤Ļ
    0.25
    æŁ¥çľĭ详æĥħ
    0.24
    segment
    0.24
    çĿĢä»ĸ
    0.24
    ilian
    0.24
    lessness
    0.23
    lov
    0.23
    Activations Density 0.882%

    No Known Activations

    This feature has no known activations.