© 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. 111021
    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
    åĽłä¸ºåľ¨
    -0.24
    åĽłä¸º
    -0.23
     muzzle
    -0.23
     lá»Ļ
    -0.23
     steals
    -0.23
    iator
    -0.23
    åĽłä¸ºæĪij们
    -0.23
    ÅĤow
    -0.23
    uffle
    -0.22
    -ste
    -0.22
    POSITIVE LOGITS
     expected
    0.26
    omain
    0.25
    审
    0.25
    å½ĵåľº
    0.25
    Expected
    0.24
    expected
    0.24
    åĹij
    0.24
    ery
    0.24
     Expect
    0.23
    æİĪ
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.