© 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. 86749
    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
    åĢĮ
    -0.29
    ONTAL
    -0.27
    INO
    -0.25
     suspension
    -0.24
    æĴIJ
    -0.24
    çĻ¾åĪĨ
    -0.24
    TEL
    -0.23
    icorn
    -0.23
    æĻ®éĢļ
    -0.22
     cuc
    -0.22
    POSITIVE LOGITS
    .microsoft
    0.27
    hower
    0.25
    (bind
    0.24
    Pred
    0.24
    çļĦä¸Ģ大
    0.23
    çļĦä¸Ģ个
    0.23
     blot
    0.22
     Velocity
    0.22
    ↵  ↵
    0.22
     wom
    0.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.