© 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. 14-TRANSCODER-HP
    7. 41763
    Prev
    Next
    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    icted
    -0.29
    åĩºçİ°åľ¨
    -0.27
    amped
    -0.26
     scarcity
    -0.25
    etto
    -0.25
    bras
    -0.24
    sono
    -0.24
    orian
    -0.24
    ponsored
    -0.24
    å¼łæī¬
    -0.24
    POSITIVE LOGITS
    Liter
    0.27
    inery
    0.27
    书ç±į
    0.26
     Literary
    0.25
     Observ
    0.25
     Fit
    0.24
    itte
    0.24
    è¶Ł
    0.24
    è¢Ń
    0.24
     Beet
    0.24
    Activations Density 0.491%

    No Known Activations