© 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. 21400
    Prev
    Next
    INDEX
    Explanations

    capable double

    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
    orate
    -0.09
    éļĶ
    -0.09
    çĢ
    -0.08
    hear
    -0.08
    воз
    -0.08
     überh
    -0.08
    åľ°åĿª
    -0.08
    vn
    -0.08
    æ··ä¹±
    -0.08
    swer
    -0.08
    POSITIVE LOGITS
    ç»ıéªĮ丰å¯Į
    0.11
    èĥ½åĬĽå¼º
    0.10
    ä»ĸæĽ¾
    0.10
    æĽ¾åľ¨
    0.10
    å±¥
    0.10
    æĽ¾ä»»
    0.09
     proven
    0.09
    æ¯ĶæĪij
    0.09
    åĮ¡
    0.09
     кÑĢай
    0.09
    Activations Density 0.030%

    No Known Activations