© 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. 32-TRANSCODER-HP
    7. 41472
    Prev
    Next
    INDEX
    Explanations

    com

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     compress
    -0.30
    ôn
    -0.28
    -con
    -0.28
    on
    -0.28
    compress
    -0.28
    oug
    -0.28
    eon
    -0.27
    .SelectCommand
    -0.26
    é¦ı
    -0.25
    con
    -0.25
    POSITIVE LOGITS
    par
    0.32
    pt
    0.31
    å½¼å¾Ĺ
    0.30
    pet
    0.30
     pet
    0.30
    paring
    0.29
    /drivers
    0.29
    PT
    0.27
    è·³
    0.27
    Par
    0.26
    Activations Density 0.012%

    No Known Activations