© 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. 52594
    Prev
    Next
    INDEX
    Explanations

    advertising and promotions

    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
    ãĤ±
    -0.30
    oble
    -0.27
    à¸Ńà¸ĩ
    -0.26
    kee
    -0.26
    inos
    -0.25
    çľĭä»ĸ
    -0.25
    enses
    -0.25
    KEN
    -0.25
    loid
    -0.25
     Bliss
    -0.24
    POSITIVE LOGITS
     teas
    0.27
    ç®į
    0.25
    æľĢéķ¿
    0.25
     exp
    0.24
    eturn
    0.23
    CAP
    0.23
    .sheet
    0.23
    æĻļ
    0.23
    æĻļæĬ¥
    0.23
    íĻľ
    0.23
    Activations Density 0.005%

    No Known Activations