© 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. 97164
    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
    elor
    -0.28
    tron
    -0.27
     rewind
    -0.27
    æīĢèĥ½
    -0.26
    ä»ĥ
    -0.25
    бе
    -0.25
    æ©Ħæ¦Ħ
    -0.24
    orz
    -0.24
    atorio
    -0.24
    xbc
    -0.24
    POSITIVE LOGITS
    æ¯ıèĤ¡
    0.27
    macros
    0.24
     +'
    0.24
    handles
    0.24
    uggle
    0.24
     Handlers
    0.24
    _handle
    0.24
    ·¨
    0.23
    ung
    0.23
     handle
    0.23
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.