© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 111910
    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
    çļĦæĦıä¹ī
    -0.27
    kah
    -0.26
    ä¿¡
    -0.25
     Kitt
    -0.25
    lus
    -0.25
    åĪĨæѧ
    -0.25
    顺
    -0.24
    ntag
    -0.24
    fic
    -0.24
    pur
    -0.24
    POSITIVE LOGITS
    loff
    0.28
    placement
    0.27
    ucion
    0.25
    è¾¾
    0.25
    ights
    0.24
    ä»ĸçŁ¥éģĵ
    0.24
    -placement
    0.24
     plain
    0.24
     sö
    0.24
     Reach
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.