© 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. 99089
    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
    covered
    -0.23
    é¸Ń
    -0.23
     specializing
    -0.23
    ais
    -0.23
    Everybody
    -0.22
    oglob
    -0.22
    ARING
    -0.22
    _ASSUME
    -0.22
    çī¹ä»·
    -0.22
     ducks
    -0.21
    POSITIVE LOGITS
    enza
    0.25
    åĴĢ
    0.24
    agraph
    0.24
    orean
    0.23
     Ut
    0.23
     Partnership
    0.23
     implic
    0.23
     applic
    0.22
    à¹Ģà¸Ĺศ
    0.22
    olec
    0.22
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.