© 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. 52507
    Prev
    Next
    INDEX
    Explanations

    disclaimers and advice

    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
     COPYRIGHT
    -0.26
    éļ¾æĢª
    -0.25
    æįĨç»ij
    -0.25
    åģļåĪ°äºĨ
    -0.25
    dll
    -0.25
    bourg
    -0.24
    lags
    -0.24
    èĭ¦èĭ¦
    -0.24
    fits
    -0.24
    lia
    -0.24
    POSITIVE LOGITS
    0.33
     of
    0.31
     present
    0.31
    ons
    0.30
     from
    0.29
     in
    0.28
    vol
    0.28
    hä
    0.27
    tha
    0.27
     next
    0.25
    Activations Density 0.016%

    No Known Activations