© 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. 39337
    Prev
    Next
    INDEX
    Explanations

    during the course of

    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
    ç½´
    -0.11
    LEV
    -0.09
    _accessible
    -0.09
    åħĭèݱ
    -0.09
    ÑģÑĤо
    -0.09
    æĶ¯æŀ¶
    -0.09
     Wheels
    -0.09
    ëĩĮ
    -0.08
    outil
    -0.08
    ä¼łå¥ĩ
    -0.08
    POSITIVE LOGITS
    æ´»åĬ¨ä¸Ń
    0.12
    å·¥ä½ľä¸Ń
    0.11
    å±¥è¡Į
    0.11
    è¿ĩç¨ĭä¸Ń
    0.10
    è¿ĩç¨ĭå½ĵä¸Ń
    0.10
    æŃ£å¸¸çļĦ
    0.10
    飵
    0.09
     duties
    0.09
    ãģĨãģ¡ãģ«
    0.09
    onas
    0.09
    Activations Density 0.049%

    No Known Activations