© 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. 21311
    Prev
    Next
    INDEX
    Explanations

    how to

    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
    çļĦä¸ĢäºĽ
    -0.09
     cle
    -0.08
    ä¸įåĨįæĺ¯
    -0.08
    hid
    -0.08
    æ·ĭ
    -0.08
    ä¸Ģä¸ĭ
    -0.08
    æīįæĺ¯çľŁæŃ£
    -0.08
    è¿ĺä¸į
    -0.08
    æĢİä¹Īä¼ļ
    -0.08
    ables
    -0.07
    POSITIVE LOGITS
    æ¡Ģ
    0.09
    ayar
    0.09
    çĴĢ
    0.09
    andest
    0.09
    è¿Ļæł·çļĦè¯Ŀ
    0.09
    ocab
    0.09
    jet
    0.09
    鬼
    0.09
    ä¸įäºĨ解
    0.09
    ocard
    0.09
    Activations Density 0.023%

    No Known Activations