© 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. 30-TRANSCODER-HP
    7. 97155
    Prev
    Next
    INDEX
    Explanations

    poly/oli

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    uchs
    -0.25
    ught
    -0.25
    ведиÑĤе
    -0.25
     vat
    -0.24
    ova
    -0.24
    稳
    -0.24
    wan
    -0.24
     parseFloat
    -0.24
    bedo
    -0.23
    è²Į
    -0.23
    POSITIVE LOGITS
    åĵģ
    0.31
    еле
    0.30
    copy
    0.28
    ä¼ļåIJĮ
    0.27
    _thumb
    0.25
    æŃ¥
    0.25
    ä»ĩ
    0.25
    åĸ·
    0.25
    liers
    0.25
    aco
    0.24
    Activations Density 0.899%

    No Known Activations