© 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. 10497
    Prev
    Next
    INDEX
    Explanations

    time of

    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
    è²Į
    -0.11
     Incorporated
    -0.09
    ä¸įçIJĨ
    -0.08
    滥
    -0.08
    ä¸įä½ı
    -0.08
    ä¸įå¿į
    -0.08
    ä¼´
    -0.08
     Baton
    -0.08
    æľºç»Ħ
    -0.08
    ä¸ĢåĪĨéĴŁ
    -0.08
    POSITIVE LOGITS
    ä¹ĭæŶ
    0.12
    undy
    0.10
    ustum
    0.10
    éĵĦ
    0.10
    夹
    0.09
    æīĢåľ¨
    0.09
    Keyboard
    0.09
    æīįçŁ¥éģĵ
    0.09
    å§Ĭ
    0.09
    arest
    0.09
    Activations Density 0.262%

    No Known Activations