© 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. 19372
    Prev
    Next
    INDEX
    Explanations

    rather than

    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¿Ļå¥Ĺ
    -0.11
    æĪij没æľī
    -0.11
    ä¸į该
    -0.10
    ä¸įå±ŀäºİ
    -0.09
    è¿ĺæĥ³
    -0.09
    è¿Ļä¸Ģå¹´
    -0.09
    ä¸įåºĶ该
    -0.09
    èĮ¸
    -0.09
    è¿ĺåĮħæĭ¬
    -0.09
    çļĦ羣å®ŀ
    -0.09
    POSITIVE LOGITS
    ä»ħä»ħ
    0.12
     ones
    0.12
    ä¸Ģåij³
    0.12
     vice
    0.10
    æľīä»»ä½ķ
    0.10
    åıªæĺ¯
    0.10
    åıįä¹ĭ
    0.10
    éĿł
    0.10
     пÑĢоÑģÑĤо
    0.10
    mere
    0.10
    Activations Density 0.032%

    No Known Activations