© 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. 57026
    Prev
    Next
    INDEX
    Explanations

    costs or price

    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
    æĮ£éĴ±
    -0.11
    èµļéĴ±
    -0.10
    ç´§å¯Ĩç»ĵåIJĪ
    -0.10
    å½¢æĢģ
    -0.09
    æľįåĬ¡æ°´å¹³
    -0.09
     dil
    -0.09
    langs
    -0.09
    ä¸ĢèĦļ
    -0.09
    æ··æ·Ĩ
    -0.09
    红åĪ©
    -0.09
    POSITIVE LOGITS
    ä¸į失
    0.09
    sus
    0.09
    é¡¿
    0.08
     ÑĤÑĭÑģÑıÑĩ
    0.08
    æĪŁ
    0.08
    è¿Ń
    0.08
    çĶ·ç¥ŀ
    0.08
    ÑĨов
    0.08
    åIJĪçIJĨçļĦ
    0.08
    æļ´
    0.08
    Activations Density 0.064%

    No Known Activations