© 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. 23933
    Prev
    Next
    INDEX
    Explanations

    Sports teams and conferences

    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
    ä¸įèµ·
    -0.28
    鼨
    -0.27
    .toFloat
    -0.27
    åĩºåħ¥å¢ĥ
    -0.26
    ebin
    -0.26
    èĭŁ
    -0.25
    rain
    -0.25
    Cases
    -0.25
    ey
    -0.24
     BigNumber
    -0.24
    POSITIVE LOGITS
    äºĴ缸
    0.27
     classmates
    0.26
    WD
    0.25
    çļĦç«ŀäºī
    0.25
    äºī龸
    0.25
    伦
    0.24
    交æµģ
    0.24
    สมาà¸Ĭ
    0.24
    ç«ŀäºī
    0.24
     regular
    0.24
    Activations Density 0.056%

    No Known Activations