© 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. 57857
    Prev
    Next
    INDEX
    Explanations

    learning outcomes education goals

    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
    侵害
    -0.09
    rÃŃ
    -0.08
     pul
    -0.08
    rex
    -0.08
    ä¸ĢåĽ¢
    -0.08
    çļĦ帮åĬ©
    -0.08
    Winner
    -0.08
    æĹĹèĪ°åºĹ
    -0.08
    æĬ±åĽ¢
    -0.08
    å¥
    -0.08
    POSITIVE LOGITS
    æİĮæı¡
    0.11
    åѦåĪ°
    0.10
    CEED
    0.10
    æŁĿ
    0.09
    èIJ½åľ¨
    0.09
    è¡®
    0.09
    UGHT
    0.09
    rray
    0.09
    äºĨ解
    0.09
    æİĮæı¡äºĨ
    0.09
    Activations Density 0.072%

    No Known Activations