© 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. 19398
    Prev
    Next
    INDEX
    Explanations

    average rating

    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
    aurus
    -0.09
    宥
    -0.09
    æ´²
    -0.09
    æ´ĭæ´ĭ
    -0.09
    ched
    -0.09
    æĪijåıijçİ°
    -0.08
    å·¨æĺŁ
    -0.08
    ä¸ŃåĽ½æ¢¦
    -0.08
    西åįĹ
    -0.08
    èµ°å¾Ĺ
    -0.08
    POSITIVE LOGITS
    át
    0.09
    åİķ
    0.08
    oxic
    0.08
     Fulton
    0.08
    ç¨ĭ度
    0.08
     Laurie
    0.08
    'utilisation
    0.08
    æĢ»ä¹ĭ
    0.08
     interviewer
    0.08
    访è°Ī
    0.08
    Activations Density 0.008%

    No Known Activations