© 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. 97152
    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
    çļĦæľ¬è´¨
    -0.25
    æľ¬è´¨
    -0.25
    Ess
    -0.25
    æ½®æµģ
    -0.24
    ä¸Ģ件äºĭæĥħ
    -0.24
    åIJ¹
    -0.23
    Keys
    -0.23
    emy
    -0.23
    Attachments
    -0.23
     essentials
    -0.23
    POSITIVE LOGITS
    æ´¼
    0.28
    对åħ¬åı¸
    0.26
    è¶ĬæĿ¥
    0.25
     Non
    0.25
    åį°è±¡æ·±åĪ»
    0.24
    rück
    0.24
     Paras
    0.23
     ged
    0.23
     Fits
    0.23
     shortest
    0.23
    Activations Density 0.020%

    No Known Activations

    This feature has no known activations.