© 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. 130318
    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
    润
    -0.32
    åŁĭ
    -0.28
    å¯ĴåĨ·
    -0.26
    nowrap
    -0.26
    è°¢
    -0.25
    åŀĤ
    -0.25
     RI
    -0.25
    æķ¬ä¸ļ
    -0.25
    å¯Ĩå°ģ
    -0.24
     eup
    -0.24
    POSITIVE LOGITS
    leshoot
    0.26
    çĸ¤
    0.26
    gment
    0.26
    åŀĵ
    0.25
    attend
    0.25
    à§İ
    0.25
    ä¸İä¸ŃåĽ½
    0.25
    нал
    0.24
    æĥ³èµ·æĿ¥
    0.24
    å£
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.