© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12046
    Prev
    Next
    INDEX
    Explanations

    product lines

    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
    è¢Ĵ
    -0.10
    æĺ¯ä¸Ģ座
    -0.10
    ä¸Ģ座
    -0.09
    çIJIJ
    -0.09
    æ°´æ³µ
    -0.08
    èĩĥ
    -0.08
    æĿijéķĩ
    -0.08
    èµ°å»Ĭ
    -0.08
    èij¡èIJĦéħĴ
    -0.08
    ook
    -0.08
    POSITIVE LOGITS
    å¸ĤéĿ¢ä¸Ĭ
    0.11
    å¸Ĥåľºä¸Ĭ
    0.10
    å¢ŀéĩı
    0.10
    éħįæĸ¹
    0.10
    çĶ¨éĩı
    0.10
    åĵģçīĮçļĦ
    0.09
    æĸ°äº§åĵģ
    0.09
    ä¼ĺè´¨çļĦ
    0.09
    ä¸ĸçķĮä¸Ĭ
    0.09
    åĵģç§į
    0.09
    Activations Density 0.161%

    No Known Activations