© 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. 87505
    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
    uitive
    -0.27
    ographically
    -0.26
    æ£ĺ
    -0.26
    éĶĻäºĨ
    -0.25
    ,âĢ¦
    -0.25
    çįĴ
    -0.24
    ensburg
    -0.24
     getUsername
    -0.24
    èĩ´å¯Į
    -0.23
    .dex
    -0.23
    POSITIVE LOGITS
    ä»ħ次äºİ
    0.31
    第äºĮ个
    0.26
    ackers
    0.26
    Plant
    0.25
     Plant
    0.25
    ç»Ļåĩº
    0.25
     conduc
    0.24
    æ¤įçī©
    0.24
    æĶ¾è¿Ľ
    0.24
    æĸ½è¡Į
    0.23
    Activations Density 0.025%

    No Known Activations

    This feature has no known activations.