© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50470
    Prev
    Next
    INDEX
    Explanations

    finding links and pages

    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
    æĤ¬æĮĤ
    -0.10
    æľ¬æĽ¸
    -0.10
    çĴľ
    -0.09
    æłı缮
    -0.09
    寸
    -0.09
    åİĺ
    -0.09
    æĮīè§Ħå®ļ
    -0.09
    ãĤªãĥ³
    -0.09
    ieu
    -0.09
    奥æŀĹåĮ¹
    -0.09
    POSITIVE LOGITS
    ç¿Ģ
    0.10
    åľ¨è¿Ļæĸ¹éĿ¢
    0.09
    ä¸İæѤ
    0.09
    æ´ŀ
    0.09
    仲
    0.08
    éªĮ
    0.08
    âĩ§
    0.08
    http
    0.08
    è¿Ļ两
    0.08
    è¿Ļ两个
    0.08
    Activations Density 0.289%

    No Known Activations