© 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. 33-TRANSCODER-HP
    7. 54823
    Prev
    Next
    INDEX
    Explanations

    Code or instructions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    -aff
    -0.31
    ections
    -0.29
    aff
    -0.27
    éĵħ
    -0.27
     Aff
    -0.27
    æķħ
    -0.26
    hots
    -0.26
     <![
    -0.26
    åįĪ
    -0.25
     lunches
    -0.25
    POSITIVE LOGITS
    rä
    0.29
    bö
    0.28
    IPH
    0.27
    ıc
    0.26
    atham
    0.24
    енко
    0.24
    chl
    0.24
    Æı
    0.23
     Sultan
    0.23
    toi
    0.23
    Activations Density 0.009%

    No Known Activations