© 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. 128906
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åī¯
    -0.26
    æ³Ĺ
    -0.25
     Davies
    -0.25
    æĺ¯éŁ©åĽ½
    -0.25
    å®ŀåĬĽ
    -0.25
     vice
    -0.25
    LEE
    -0.24
    éĴº
    -0.24
    _authenticated
    -0.24
    thon
    -0.24
    POSITIVE LOGITS
    ean
    0.31
    è¿Ŀ
    0.29
     Hom
    0.28
    åľ¨ä¸Ģèµ·
    0.26
    >(()
    0.26
    azon
    0.25
    utherford
    0.25
    åĬĽè¿ĺæĺ¯
    0.25
     Hearts
    0.24
     foreseeable
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.