© 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. 17568
    Prev
    Next
    INDEX
    Explanations

    chess championship

    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
    ocene
    -0.09
    幺
    -0.09
    æģ£
    -0.09
    饮æĸĻ
    -0.08
    ream
    -0.08
    enza
    -0.08
    æŁĶæĢ§
    -0.08
    ewire
    -0.08
    åľ¨äº¬
    -0.08
    isha
    -0.08
    POSITIVE LOGITS
    æ£ĭ
    0.11
    ä»Ĺ
    0.10
     chess
    0.10
    大å±Ģ
    0.09
    âĻŁ
    0.09
    çİĭåĽ½
    0.09
    æŁĿ
    0.09
     Pruitt
    0.09
    æ®ĺ
    0.09
    为é¦ĸçļĦ
    0.09
    Activations Density 0.021%

    No Known Activations