© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20409
    Prev
    Next
    INDEX
    Explanations

    criticism or negative actions

    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
    ä¸ĸ代
    -0.10
    襲
    -0.09
    æİł
    -0.09
    çĬ¯
    -0.09
    imiters
    -0.09
    ä¸įåı¯éģ¿åħį
    -0.08
    èŀŁ
    -0.08
    褥
    -0.08
    çķĮçļĦ
    -0.08
    akers
    -0.08
    POSITIVE LOGITS
    åģľè½¦
    0.10
    éķ¿æ±Ł
    0.09
    çĸijä¼¼
    0.09
    举
    0.09
    è¸ŀ
    0.08
    æĺ¯ä»Ģä¹Īåij¢
    0.08
    é£İè²Į
    0.08
    /dashboard
    0.08
    çļĦéŃħåĬĽ
    0.08
    LES
    0.08
    Activations Density 0.085%

    No Known Activations