© 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. 20-TRANSCODER-HP
    7. 108711
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    A
    -0.27
     jour
    -0.26
     Intern
    -0.25
     Ev
    -0.24
     Iowa
    -0.24
     A
    -0.24
     pass
    -0.24
     EV
    -0.24
    [
    -0.23
    è¹ĭ
    -0.23
    POSITIVE LOGITS
    berman
    0.28
    dux
    0.26
    çļĦä½įç½®
    0.26
    _challenge
    0.25
    æĿµ
    0.25
    @index
    0.25
    éĺµ
    0.25
     untranslated
    0.24
    ä¸įèĩ³äºİ
    0.24
    beros
    0.24
    Activations Density 7.118%

    No Known Activations

    This feature has no known activations.