© 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. 21717
    Prev
    Next
    INDEX
    Explanations

    biological and production metrics

    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¸Ģåijĺ
    -0.10
    ä¼ĺè´¨çļĦ
    -0.09
     priced
    -0.09
    _trampoline
    -0.09
    è¾ĥ大çļĦ
    -0.09
    é¹Ĭ
    -0.08
    å·¥èīºåĵģ
    -0.08
    æļĤç¼ĵ
    -0.08
    å¾Ī大çļĦ
    -0.08
    æĪİ
    -0.08
    POSITIVE LOGITS
    çĶŁæ´»æ°´å¹³
    0.12
    å®ŀéĻħ
    0.12
     overall
    0.11
    èĥ½åĬĽåĴĮ
    0.11
    æķ´ä½ĵ
    0.11
    æĬĢæľ¯æ°´å¹³
    0.11
    çļĦæķ´ä½ĵ
    0.10
    è¦ĨçĽĸçİĩ
    0.10
     total
    0.10
    çļĦå®ŀéĻħ
    0.10
    Activations Density 1.057%

    No Known Activations