© 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. 88619
    Prev
    Next
    INDEX
    Explanations

    second

    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
    Not in Any Lists

    No Comments

    Negative Logits
     HOUR
    -0.26
    ToOne
    -0.26
    Ot
    -0.25
    ä¸Ģæĸ¹éĿ¢
    -0.25
     mouseX
    -0.25
    æĥķ
    -0.25
    wolf
    -0.24
    è¯ī讼
    -0.24
     removeFrom
    -0.24
    çļĦä¸ĢéĿ¢
    -0.23
    POSITIVE LOGITS
    \Queue
    0.29
     most
    0.29
     worst
    0.28
    æľĢåħ·
    0.28
     happiest
    0.27
    æľĢé«ĺçļĦ
    0.27
    æľĢæľī
    0.27
     highest
    0.27
     hottest
    0.27
    æľĢåıĹ欢è¿İ
    0.27
    Activations Density 0.018%

    No Known Activations