© 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. 21925
    Prev
    Next
    INDEX
    Explanations

    As

    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
    Negative Logits
    ä¼ļå±ķä¸Ńå¿ĥ
    -0.28
     trailer
    -0.28
    lien
    -0.24
    adio
    -0.24
    åºĬ
    -0.24
    æĬ¥è®°èĢħ
    -0.24
    åĽłåŃIJ
    -0.23
    ÑģÑĤеÑĢ
    -0.23
    ÑģÑĢ
    -0.23
    æį
    -0.23
    POSITIVE LOGITS
    _supply
    0.29
     deposits
    0.28
    ley
    0.28
    تخ
    0.28
    READING
    0.28
     Reading
    0.26
     reading
    0.25
     ìī½
    0.25
     Depos
    0.25
    als
    0.25
    Activations Density 0.000%

    No Known Activations