© 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. 129085
    Prev
    Next
    INDEX
    Explanations

    integrated circuits and electronics

    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
    uze
    -0.28
    resses
    -0.27
     (()
    -0.26
    mpp
    -0.25
    ØŃر
    -0.24
    æĿ¯åŃIJ
    -0.24
     cocks
    -0.23
    åľ¨æİ¥åıĹ
    -0.23
    ece
    -0.23
    ä¹ĭæĺŁ
    -0.23
    POSITIVE LOGITS
     work
    0.28
    åĢĺèĭ¥
    0.27
    idental
    0.26
    éĢĶä¸Ń
    0.26
    .setdefault
    0.25
    èı©æıIJ
    0.24
     matching
    0.24
    æĮĩ
    0.24
    urement
    0.23
     founder
    0.23
    Activations Density 0.009%

    No Known Activations