© 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. 33-TRANSCODER-HP
    7. 52740
    Prev
    Next
    INDEX
    Explanations

    team

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     teams
    -0.44
     team
    -0.43
    åĽ¢éĺŁ
    -0.42
    teams
    -0.41
     Teams
    -0.41
    Teams
    -0.41
     Team
    -0.40
    Team
    -0.39
    _team
    -0.37
     TEAM
    -0.37
    POSITIVE LOGITS
     form
    0.44
    å½¢å¼ı
    0.31
    ä¸ĩ个
    0.31
    form
    0.30
     pr
    0.30
     rom
    0.30
    uses
    0.30
     Form
    0.29
     forms
    0.29
    çļĦå½¢å¼ı
    0.28
    Activations Density 0.011%

    No Known Activations