© 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. 50016
    Prev
    Next
    INDEX
    Explanations

    reporters and bylines

    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
    ç¼ĺ
    -0.10
    æ¯Ķè¾ĥç®Ģåįķ
    -0.09
    åŀĭåı·
    -0.09
    éĿŀ常æĺİæĺ¾
    -0.09
    æŀ£
    -0.09
    åŁķ
    -0.09
    è¿ľæĻ¯
    -0.09
    otation
    -0.09
    è½®å»ĵ
    -0.09
    çģµæĦŁ
    -0.09
    POSITIVE LOGITS
    æĬ¥éģĵ
    0.15
    è®°èĢħ
    0.11
     reporters
    0.10
    è¦Ĩ
    0.10
    รายà¸ĩาà¸Ļ
    0.10
    'article
    0.09
     reporter
    0.09
    åł±å°İ
    0.09
    أخبار
    0.09
     Reporter
    0.09
    Activations Density 0.062%

    No Known Activations