© 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. 40786
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    ós
    -0.32
    oco
    -0.29
    OV
    -0.28
     the
    -0.28
    OX
    -0.28
    *",
    -0.28
    olan
    -0.27
    ewidth
    -0.27
     oh
    -0.27
    ',(
    -0.27
    POSITIVE LOGITS
     Syrians
    0.32
     Pulitzer
    0.32
    3
    0.30
    2
    0.30
     Treasury
    0.30
     attorneys
    0.29
     neoliberal
    0.29
     Lebanese
    0.29
     Hezbollah
    0.29
     Carnegie
    0.28
    Activations Density 16.384%

    No Known Activations