© 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. 128920
    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
     Seymour
    -0.28
    structural
    -0.28
     ::=
    -0.24
    ectors
    -0.24
     Structural
    -0.24
     structural
    -0.24
    ëĭ´
    -0.23
    conscious
    -0.23
    .partial
    -0.23
    (Gravity
    -0.23
    POSITIVE LOGITS
    angs
    0.32
    OH
    0.28
    íķĦ
    0.25
    ä¸Ŀ
    0.25
    ай
    0.25
    Subtitle
    0.24
    å½±åĵįåĬĽçļĦ
    0.24
    ridge
    0.24
    atal
    0.23
    ä»ħ代表
    0.23
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.