© 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. 54311
    Prev
    Next
    INDEX
    Explanations

    browsing the site, holding a valid

    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
    å·´åŁº
    -0.10
    ä»»ä½ķå½¢å¼ı
    -0.10
    åĴļ
    -0.10
    é¦Ļ
    -0.09
    åı£æ°´
    -0.09
    åĶ¯ä¸ĢçļĦ
    -0.08
    éĵĽ
    -0.08
    æľĢåIJİä¸Ģ次
    -0.08
    izontal
    -0.08
    å»¶è¿Ł
    -0.08
    POSITIVE LOGITS
    æ®Ĭ
    0.09
    erville
    0.09
    ä¹ĭåľ°
    0.09
    etu
    0.08
    æĦı大
    0.08
     Kor
    0.08
    óst
    0.08
    ÑĩÑĮ
    0.08
    è¿ĩå¾Ģ
    0.08
    è¦ģåѦä¼ļ
    0.08
    Activations Density 0.001%

    No Known Activations