© 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. 52541
    Prev
    Next
    INDEX
    Explanations

    scientific/technical contexts

    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
    ition
    -0.28
    ุม
    -0.28
    è°±
    -0.27
    utive
    -0.27
    iton
    -0.26
    artment
    -0.25
     harmless
    -0.25
    itions
    -0.25
    ulously
    -0.24
    edom
    -0.24
    POSITIVE LOGITS
    lider
    0.26
    EVER
    0.25
    gies
    0.24
    åįİ缼
    0.24
    æľŁåĨħ
    0.23
    æİĸ
    0.23
     Thurs
    0.23
    ç¿¥
    0.23
    elige
    0.23
    ende
    0.22
    Activations Density 0.003%

    No Known Activations