© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 22247
    Prev
    Next
    INDEX
    Explanations

    Text snippets from varied sources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç»ĵåIJĪèµ·æĿ¥
    -0.29
    æıIJèµ·
    -0.28
    åıĮ
    -0.26
    æľ¬é¢Ĩ
    -0.26
    -relative
    -0.26
    unities
    -0.26
    èĥĥåı£
    -0.26
    ุà¸ĩ
    -0.26
    强迫
    -0.25
    ansen
    -0.25
    POSITIVE LOGITS
    TreeWidgetItem
    0.27
     Aging
    0.26
     Ball
    0.26
    (Vec
    0.25
     Blu
    0.25
    Effect
    0.25
    éªij
    0.25
    Effects
    0.25
    rcode
    0.24
    łģ
    0.24
    Activations Density 0.135%

    No Known Activations