© 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. 99253
    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
    Atom
    -0.29
    åĪ¤æĸŃ
    -0.28
    æĭĴç»Ŀ
    -0.27
     modulo
    -0.27
     reject
    -0.27
     rejection
    -0.25
    _ttl
    -0.25
    æ¯ĭ
    -0.24
    è·º
    -0.24
    åĮºåĪ«
    -0.24
    POSITIVE LOGITS
    ubo
    0.27
    Ľå»º
    0.24
     ROUND
    0.24
    éľĢ
    0.23
    uda
    0.23
    edis
    0.23
     rehabilit
    0.23
    emm
    0.23
    åĺ§
    0.23
    ukkan
    0.23
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.