© 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. 20625
    Prev
    Next
    INDEX
    Explanations

    research institute

    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
    æĥħ人
    -0.10
    饰
    -0.09
    æī¬
    -0.08
    ck
    -0.08
     Inner
    -0.08
     concentration
    -0.07
     inner
    -0.07
    è¯Ń
    -0.07
    éĩİ
    -0.07
    CONF
    -0.07
    POSITIVE LOGITS
    çīµ
    0.13
    çłĶ究éĻ¢
    0.11
    çī½
    0.11
    æĪIJç«ĭ以æĿ¥
    0.11
    éĻĦå±ŀ
    0.11
    æĵģ
    0.11
    ató
    0.11
    ä¸īæľŁ
    0.10
    æ©Łæ§ĭ
    0.10
    æĢ»æĬķèµĦ
    0.10
    Activations Density 0.071%

    No Known Activations