© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50714
    Prev
    Next
    INDEX
    Explanations

    game moves

    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
    Kay
    -0.09
    æİĴæŁ¥
    -0.09
    æĢĢ
    -0.08
    5
    -0.08
     dere
    -0.08
    éĹ¹
    -0.08
    ç¬ijçĿĢ
    -0.08
    YS
    -0.08
     exclus
    -0.08
    褥
    -0.08
    POSITIVE LOGITS
    第ä¸ĢæŃ¥
    0.11
    éĢīæĭ©
    0.11
    许åı¯
    0.10
    çļĦéĢīæĭ©
    0.10
    åı¯ä»¥éĢīæĭ©
    0.09
    æīĵåħ¥
    0.09
    ä¸Ģæīĭ
    0.09
    yntax
    0.09
    éģ¸æĵĩ
    0.09
    ä¸Ģ举
    0.09
    Activations Density 0.015%

    No Known Activations