© 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. 112823
    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
    Not in Any Lists

    No Comments

    Negative Logits
    å·¥ä½ľç«Ļ
    -0.28
    æĵ¦
    -0.27
    侧
    -0.25
    ç²¾ç¥ŀ
    -0.25
    æī¹æ¬¡
    -0.25
    bags
    -0.25
    æĻºèĥ½
    -0.25
    ossier
    -0.25
    озвÑĢаÑīаеÑĤ
    -0.24
    rement
    -0.24
    POSITIVE LOGITS
    ç»Ń约
    0.27
    iture
    0.26
    称ä¹ĭ
    0.25
    onomy
    0.24
     warmed
    0.24
    éĢļè¡Į
    0.24
    tures
    0.24
    é¾ĻéŨ
    0.23
    zers
    0.23
    copyright
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.