© 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. 97338
    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
    èĢģåĮĸ
    -0.27
    åĮĿ
    -0.24
    iev
    -0.24
    ä¸ĢèĦ¸
    -0.24
    身份
    -0.23
    åĮĸåIJĪ
    -0.23
    éĢĹ
    -0.22
     prestige
    -0.22
     intimid
    -0.22
    æľ´ç´ł
    -0.22
    POSITIVE LOGITS
    éĻ¤å¤ĸ
    0.28
    uran
    0.28
    ç»Ħ
    0.26
    éĴ®
    0.26
    ÑĢаÐ
    0.25
    NAL
    0.25
    åħ¨åĮº
    0.24
    ↵ ↵
    0.24
     BASIS
    0.24
    rap
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.