© 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. 97596
    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
    åĵ¨
    -0.31
    对æĪij
    -0.27
    ноп
    -0.26
    ippi
    -0.26
    Sense
    -0.25
    åĨ»
    -0.25
     wast
    -0.24
    ense
    -0.24
     Barnett
    -0.24
    plural
    -0.24
    POSITIVE LOGITS
    æľīæĿ¡ä»¶çļĦ
    0.29
    åŀ¦
    0.26
     surpassed
    0.26
    å¼ķèµ·çļĦ
    0.25
    .esp
    0.25
     blackmail
    0.24
    éļĻ
    0.23
    landers
    0.23
    åĢŁ
    0.23
    è¶Ĭæĺ¯
    0.23
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.