© 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. 33574
    Prev
    Next
    INDEX
    Explanations

    about us, search, contact, testimonials, follow

    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
    åİŁåĽłä¹ĭä¸Ģ
    -0.09
    ç½ij讯
    -0.09
     Garr
    -0.08
    èĴ¿
    -0.08
    æķ°é¢Ŀ
    -0.08
     Hog
    -0.08
    ç¼Ń
    -0.08
     tackled
    -0.08
     dungeons
    -0.07
    åľ¨éĤ£éĩĮ
    -0.07
    POSITIVE LOGITS
    uale
    0.09
    STANCE
    0.09
    åĪļ好
    0.08
    agal
    0.08
    sei
    0.08
    æĿ¥çļĦ
    0.08
     каÑĩ
    0.08
    æ¼ı
    0.08
     ÙĨÙĬÙĪز
    0.08
     jud
    0.08
    Activations Density 0.075%

    No Known Activations