© 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. 89009
    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
     Capitals
    -0.28
     higher
    -0.24
    original
    -0.24
    å¤ĩæ¡Ī
    -0.24
    第ä¸Ģä½į
    -0.24
    âĢ¦
    -0.24
    tower
    -0.24
    ese
    -0.23
    涨
    -0.23
    á»į
    -0.23
    POSITIVE LOGITS
    isory
    0.29
    uids
    0.28
    atura
    0.28
    ationally
    0.27
     Replay
    0.25
    ROID
    0.24
    ä¸ĭéĿ¢æĪij们
    0.24
    å±ģèĤ¡
    0.24
    isel
    0.24
    éŃĶ鬼
    0.24
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.