© 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. 62023
    Prev
    Next
    INDEX
    Explanations

    professional designations and initials

    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
    夺åıĸ
    -0.09
    ä¸Ģè§Ĵ
    -0.09
    spar
    -0.09
    æĪij没
    -0.08
    quan
    -0.08
    ayı
    -0.08
    ç·£
    -0.08
    ä¸įäºĨ
    -0.08
    iev
    -0.08
    ç¼ĺ
    -0.08
    POSITIVE LOGITS
    åIJijä¸Ĭ
    0.09
    êµIJ
    0.08
    å¼ĵ
    0.08
    èī²ç´ł
    0.08
     foe
    0.08
     conc
    0.08
    è¡ĮæĿİ
    0.08
    ä»ĸä»¬åľ¨
    0.08
     Fet
    0.08
    .equalsIgnoreCase
    0.07
    Activations Density 0.064%

    No Known Activations