© 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. 1539
    Prev
    Next
    INDEX
    Explanations

    places described with specific features

    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
    ç¼±
    -0.08
    æļijæľŁ
    -0.08
    ä¸įç»ıæĦı
    -0.08
    æĴ®
    -0.08
    wc
    -0.08
    å°±è¶Ĭ
    -0.08
    åºķ线
    -0.07
    车载
    -0.07
     УкÑĢа
    -0.07
    ç´Ĭ
    -0.07
    POSITIVE LOGITS
    jian
    0.09
    ë²½
    0.09
    梦å¢ĥ
    0.09
    è£ģ
    0.09
    é£ŀèĪ¹
    0.09
    ä¸ĵéŨ
    0.08
    æŃĮåĶ±
    0.08
    keh
    0.08
    æī§æĶ¿
    0.08
    é£İå°ļ
    0.08
    Activations Density 0.085%

    No Known Activations