© 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. 23099
    Prev
    Next
    INDEX
    Explanations

    group 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
    ä¸Ģ个好çļĦ
    -0.09
    éĥ½æĥ³
    -0.09
    idas
    -0.08
    ÙĪÙĩ
    -0.08
    irs
    -0.08
    æ¯ıä¸Ģ个人
    -0.08
     Mov
    -0.08
    aden
    -0.08
    æ¦ķ
    -0.08
    ANE
    -0.07
    POSITIVE LOGITS
    Matchers
    0.10
    絡
    0.09
    åĩłåIJį
    0.09
    åIJĦç±»
    0.09
    зи
    0.09
    äººåľ¨
    0.09
    æĦĶ
    0.08
    estar
    0.08
    Freedom
    0.08
    足以
    0.08
    Activations Density 0.190%

    No Known Activations