© 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. 86994
    Prev
    Next
    INDEX
    Explanations

    general text

    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
     enquiry
    -0.27
    å±Ģå±Ģéķ¿
    -0.26
    åħ¨å¤©
    -0.25
     Pru
    -0.25
     diam
    -0.25
    èĺ¸
    -0.24
     commod
    -0.23
    acks
    -0.23
    åı¯ä»¥æĬĬ
    -0.23
    举é£İ
    -0.23
    POSITIVE LOGITS
    yd
    0.28
    qb
    0.26
    说éģĵ
    0.26
    ugg
    0.26
    볤
    0.25
    à¸ļ
    0.25
    ï¼īãĢģ
    0.25
    é«ĺæ°´å¹³
    0.24
    è¿Ļä¸ĢçĤ¹
    0.24
    åį´
    0.23
    Activations Density 0.002%

    No Known Activations