© 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. 31-TRANSCODER-HP
    7. 17930
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     lat
    -0.28
     latency
    -0.27
     golden
    -0.26
    oble
    -0.26
    ow
    -0.26
    lat
    -0.26
    LED
    -0.25
    -lat
    -0.25
    golden
    -0.24
     lit
    -0.24
    POSITIVE LOGITS
     nipple
    0.27
    .ham
    0.26
    leck
    0.25
     (!((
    0.25
    fram
    0.25
    èĤīä½ĵ
    0.24
    éĺIJ
    0.24
    å¡«åħħ
    0.24
    åĵ¨
    0.24
     manufactures
    0.24
    Activations Density 0.389%

    No Known Activations