© 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. 86982
    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
    ophage
    -0.28
    olutely
    -0.27
    é¡·
    -0.27
    senal
    -0.26
     rej
    -0.26
    Unmount
    -0.26
     nevertheless
    -0.26
     desper
    -0.25
     damit
    -0.24
    åĩ½
    -0.24
    POSITIVE LOGITS
    åIJĦèĩªçļĦ
    0.27
    avig
    0.27
     Ps
    0.26
    Rh
    0.25
    ä»ĸèĩªå·±
    0.25
    ä¹ĭ称
    0.24
    etchup
    0.24
    iant
    0.23
    izards
    0.23
     Outcome
    0.23
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.