© 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. 31-TRANSCODER-HP
    7. 19048
    Prev
    Next
    INDEX
    Explanations

    research studies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gio
    -0.29
     bio
    -0.28
    .bio
    -0.28
    ãĥIJãĤ¤
    -0.26
    ugs
    -0.26
     Collect
    -0.26
    .Emit
    -0.26
     Submission
    -0.24
    collect
    -0.24
     collecting
    -0.24
    POSITIVE LOGITS
     sed
    0.37
    itud
    0.32
    sed
    0.30
    astes
    0.29
     Sed
    0.28
    PTY
    0.26
    éĺ³åİ¿
    0.26
    ä¸ľè¥¿
    0.25
     insured
    0.25
    ç»ıéªĮåĴĮ
    0.25
    Activations Density 1.094%

    No Known Activations