© 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. 11379
    Prev
    Next
    INDEX
    Explanations

    pay per click advertising

    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
    _pins
    -0.09
    大ä¼Ĺ
    -0.09
    æļ´é£İ
    -0.08
    ÙħÙĪا
    -0.08
    WARE
    -0.08
    åĨįçĶŁ
    -0.08
    éĶ¦æłĩ
    -0.08
    象å¾ģ
    -0.08
    åįĩåįİ
    -0.08
    å·¥ç¨ĭ建设
    -0.08
    POSITIVE LOGITS
    çľł
    0.11
    广åijĬ
    0.11
    åŀĤ
    0.10
    æīĵèµ¢
    0.10
     Ads
    0.10
    åĩĨç¡®æĢ§
    0.10
    .bd
    0.10
    æķ´æ²»
    0.09
    计
    0.09
    踵
    0.09
    Activations Density 0.100%

    No Known Activations