© 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. 38602
    Prev
    Next
    INDEX
    Explanations

    et al citations

    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
    Negative Logits
     et
    -1.20
    _et
    -0.88
    (et
    -0.85
    .et
    -0.79
     Et
    -0.76
    Et
    -0.75
    -et
    -0.73
     ET
    -0.62
    _ET
    -0.56
    ET
    -0.48
    POSITIVE LOGITS
     roma
    0.36
     vl
    0.31
     saturn
    0.30
     Åļw
    0.30
     zf
    0.30
     sca
    0.29
     sce
    0.29
     cla
    0.29
     milano
    0.28
     kend
    0.28
    Activations Density 33.403%

    No Known Activations