© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19202
    Prev
    Next
    INDEX
    Explanations

    exist or not exist

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è²Ĥ
    -0.09
    éķĴ
    -0.09
     Pron
    -0.08
    ç»·
    -0.08
    Portable
    -0.08
    çīĿ
    -0.08
    è°´
    -0.08
    едÑĮ
    -0.08
    çİ©åħ·
    -0.08
    rück
    -0.08
    POSITIVE LOGITS
     exist
    0.31
     exists
    0.29
     existence
    0.29
    åŃĺåľ¨
    0.28
    åŃĺåľ¨çļĦ
    0.27
    exists
    0.27
    çļĦåŃĺåľ¨
    0.27
     ì¡´ìŀ¬
    0.27
     Exists
    0.26
     Exist
    0.26
    Activations Density 0.168%

    No Known Activations