© 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. 23-TRANSCODER-HP
    7. 24185
    Prev
    Next
    INDEX
    Explanations

    Comparisons or alternatives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĽĦ
    -0.26
    .TryParse
    -0.26
    PLICATE
    -0.26
    pliers
    -0.25
    ponents
    -0.25
    _secs
    -0.25
    uppe
    -0.25
    gran
    -0.25
    sse
    -0.24
    erais
    -0.24
    POSITIVE LOGITS
    éĤ£ä¹Īå¤ļ
    0.31
    ATA
    0.29
     amount
    0.29
    ç¨ĭ度
    0.29
    çļĦç¨ĭ度
    0.28
    ata
    0.27
    è¿Ļä¹Īå¤ļ
    0.27
    ew
    0.26
    form
    0.26
    æł·åŃIJ
    0.25
    Activations Density 0.007%

    No Known Activations