© 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. 111107
    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
    rias
    -0.31
    ç²Ĺ
    -0.27
    çĽ¸å¯¹äºİ
    -0.26
    illos
    -0.24
    Intermediate
    -0.24
    (indent
    -0.23
    าà¸ĩ
    -0.23
    INA
    -0.23
    nnen
    -0.23
    ä¾ĿéĿł
    -0.23
    POSITIVE LOGITS
     Front
    0.28
    -pic
    0.26
     Amazing
    0.25
    éĢŁåº¦å¿«
    0.25
     Squad
    0.24
    åħīæĺİ
    0.24
    Pic
    0.23
    æĹ°
    0.23
    æ´¾åĩº
    0.23
    åĩºåİĤ
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.