© 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. 111305
    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
    è¿ĻæĿ¡
    -0.28
    tip
    -0.26
    ä¸Ģæ¢Ŀ
    -0.26
    -tip
    -0.26
    ipy
    -0.25
    第ä¸ĢæĿ¡
    -0.25
    åĭ¾
    -0.25
    rtl
    -0.24
    ä¸ĢæĿ¡
    -0.24
    Tip
    -0.24
    POSITIVE LOGITS
    iales
    0.28
    avors
    0.27
    protect
    0.27
    ectors
    0.24
    éĩijåĪļ
    0.24
     TRADE
    0.24
    [layer
    0.23
     Protect
    0.23
    istrict
    0.23
    æĮ«
    0.23
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.