© 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. 40754
    Prev
    Next
    INDEX
    Explanations

    Glycosylation/Glycolysis

    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
    éments
    -0.27
     attempted
    -0.25
    ä¸įèµ·
    -0.25
    Grün
    -0.25
     attainment
    -0.24
    맴
    -0.24
     депÑĥÑĤ
    -0.24
     attain
    -0.23
     allot
    -0.23
    ä¾ĭå¤ĸ
    -0.23
    POSITIVE LOGITS
    g
    0.41
    gos
    0.38
    nc
    0.38
    rc
    0.36
    ges
    0.36
    ged
    0.35
    tok
    0.35
    sc
    0.35
    p
    0.33
    gs
    0.33
    Activations Density 3.301%

    No Known Activations