© 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. 27-TRANSCODER-HP
    7. 57000
    Prev
    Next
    INDEX
    Explanations

    non-English characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (OP
    -0.28
    pull
    -0.28
     tempered
    -0.26
    æľ¬äºº
    -0.26
    ToPoint
    -0.26
    Attached
    -0.25
    /trunk
    -0.25
    stitute
    -0.24
    ieurs
    -0.24
    /Desktop
    -0.24
    POSITIVE LOGITS
    è¡Ĺ
    0.28
    oad
    0.25
     overlaps
    0.25
    åIJij社ä¼ļ
    0.25
    ầu
    0.25
    aji
    0.24
    vä
    0.24
    éĽĨä½ĵ
    0.24
    天èĬ±æĿ¿
    0.24
    ìħĢ
    0.24
    Activations Density 0.003%

    No Known Activations