© 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. 44219
    Prev
    Next
    INDEX
    Explanations

    age

    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
    Negative Logits
    yz
    -0.27
    éģĩä¸Ĭ
    -0.26
    Marshal
    -0.25
    onor
    -0.23
     bak
    -0.23
    éĿ¢æĿ¡
    -0.23
    old
    -0.23
    èIJ½åħ¥
    -0.23
    æĹĹå¸ľ
    -0.23
    맨
    -0.23
    POSITIVE LOGITS
     one
    0.45
     One
    0.36
    çļĦä¸Ģ个
    0.36
    ä¸Ģ个
    0.35
     одного
    0.35
     одной
    0.34
    _one
    0.33
    ä¸Ģ页
    0.33
    One
    0.32
     uno
    0.32
    Activations Density 0.003%

    No Known Activations