© 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. 52702
    Prev
    Next
    INDEX
    Explanations

    now that

    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
    éĤ£æŶåĢĻ
    -0.10
    çļĦå°±æĺ¯
    -0.09
    éĤ£æŶ
    -0.09
    istes
    -0.09
    éĤ£ä¸ªæŶåĢĻ
    -0.08
    毫ä¸įçĬ¹è±«
    -0.08
    æ¯ıå½ĵ
    -0.08
    ä¸Ģå¹ķ
    -0.08
    åľ¨æѤ
    -0.08
    æĬ¼
    -0.08
    POSITIVE LOGITS
    çľĭæĿ¥
    0.11
    ted
    0.10
    eh
    0.10
    isd
    0.09
    gro
    0.09
    ç¬ĶèĢħ
    0.09
    pent
    0.09
    ting
    0.09
    gar
    0.09
    æĪij们
    0.09
    Activations Density 0.004%

    No Known Activations