© 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. 131176
    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
    iska
    -0.28
     scrolled
    -0.25
    æĻ¯
    -0.24
     FAILURE
    -0.24
      ↵    ↵
    -0.24
    åı¯èĥ½å¯¼èĩ´
    -0.23
    _DT
    -0.23
     Advis
    -0.23
    åı¯èĥ½
    -0.23
     favour
    -0.22
    POSITIVE LOGITS
     raising
    0.27
    .raise
    0.27
    举
    0.26
    ence
    0.26
    summ
    0.25
     her
    0.24
     ÑģÑĤо
    0.24
    Summary
    0.23
    ographic
    0.23
    ENCE
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.