© 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. 38553
    Prev
    Next
    INDEX
    Explanations

    pan

    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
    a
    -0.38
     Est
    -0.28
     Episcopal
    -0.26
    ep
    -0.26
     Holding
    -0.25
    est
    -0.24
     epile
    -0.24
     reigning
    -0.24
     Celtic
    -0.24
    Hold
    -0.24
    POSITIVE LOGITS
    asher
    0.29
    Å¡ÃŃ
    0.29
    ror
    0.29
    ubern
    0.28
    kaar
    0.28
    æĿµ
    0.28
    UTE
    0.27
    uate
    0.27
    èĪį
    0.27
    ute
    0.27
    Activations Density 4.167%

    No Known Activations