© 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. 88984
    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
    atar
    -0.31
    ãĤ¶ãĥ¼
    -0.30
    ATAR
    -0.27
    icum
    -0.27
    asers
    -0.26
    asic
    -0.26
    æľĥèŃ°
    -0.26
    idian
    -0.26
    undef
    -0.25
     Democr
    -0.25
    POSITIVE LOGITS
    è¿¥
    0.30
    ãĢĢ
    0.29
     edge
    0.27
    /im
    0.27
    /com
    0.25
     uw
    0.25
    èĦļ
    0.25
    zo
    0.25
    缩
    0.25
     cosm
    0.24
    Activations Density 0.020%

    No Known Activations

    This feature has no known activations.