© 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. 52713
    Prev
    Next
    INDEX
    Explanations

    technical/scientific jargon

    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
    éĢļ
    -0.56
    Ar
    -0.36
     Ar
    -0.33
    AR
    -0.33
    ar
    -0.32
    .ar
    -0.30
    ãĤ´ãĥ¼ãĥ«
    -0.30
    _ar
    -0.30
    arest
    -0.29
    .Ar
    -0.29
    POSITIVE LOGITS
    æľīæľŁ
    0.28
    éģı
    0.27
    èIJ¥
    0.26
    кÑĢо
    0.26
    cation
    0.26
     Container
    0.24
    enance
    0.24
    æĬij
    0.24
    abol
    0.24
    cq
    0.24
    Activations Density 0.138%

    No Known Activations