© 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. 32-TRANSCODER-HP
    7. 41139
    Prev
    Next
    INDEX
    Explanations

    leaders and politicians

    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
    贯穿
    -0.27
    ula
    -0.27
    ä¾Ľæ°´
    -0.26
    ãģ«å¯¾
    -0.26
     cent
    -0.26
    ç®ĹäºĨ
    -0.25
     corres
    -0.24
    locate
    -0.24
     polit
    -0.23
     political
    -0.23
    POSITIVE LOGITS
    设计
    0.32
    -design
    0.31
     Design
    0.29
    design
    0.29
    _design
    0.27
    Design
    0.27
     design
    0.27
    -functions
    0.25
     Wheel
    0.25
    å¢ŀåĢ¼
    0.25
    Activations Density 0.021%

    No Known Activations