© 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. 35-TRANSCODER-HP
    7. 40401
    Prev
    Next
    INDEX
    Explanations

    business and economics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sector
    -1.21
     Sector
    -1.15
    sector
    -1.14
     sectors
    -1.09
    Sector
    -1.09
     sect
    -0.96
    _sector
    -0.95
    -sector
    -0.93
    sect
    -0.90
     Sect
    -0.87
    POSITIVE LOGITS
    縱
    0.25
    -gen
    0.25
    (condition
    0.24
    -IS
    0.24
    /system
    0.24
    AFE
    0.23
    Ļ¶
    0.23
    島
    0.23
     proxies
    0.23
    .Atomic
    0.23
    Activations Density 12.956%

    No Known Activations