© 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. 22-TRANSCODER-HP
    7. 131026
    Prev
    Next
    INDEX
    Explanations

    chance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çľĭäºĨ
    -0.30
    s
    -0.28
    T
    -0.28
     everywhere
    -0.27
     Superior
    -0.26
    ä¸ĵéĹ¨ä¸º
    -0.26
    Maps
    -0.26
    話ãĤĴ
    -0.26
    R
    -0.26
     viá»ĩc
    -0.25
    POSITIVE LOGITS
    kest
    0.30
    åĩºå¤Ħ
    0.29
    mil
    0.28
    jah
    0.27
    代
    0.27
    abbr
    0.27
    zelf
    0.26
    illard
    0.26
    ilyn
    0.26
    åĪĩåħ¥
    0.26
    Activations Density 0.019%

    No Known Activations