© 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. 62575
    Prev
    Next
    INDEX
    Explanations

    dates and organizations

    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
    ä¸ĥæľĪ
    -0.17
     Sept
    -0.16
    July
    -0.15
    æļijæľŁ
    -0.15
     July
    -0.15
    ç§ĭ
    -0.15
    ä¸īåŃ£åº¦
    -0.15
    Sept
    -0.15
    ä¸ĭåįĬå¹´
    -0.14
     sept
    -0.14
    POSITIVE LOGITS
    æĺ¥èĬĤæľŁéĹ´
    0.26
    æĺ¥èĬĤ
    0.22
    å¯Ĵåģĩ
    0.22
    æĸ°æĺ¥
    0.20
    æĸ°å¹´
    0.20
    å¯ĴåĨ¬
    0.19
    åĨ¬
    0.18
     winter
    0.18
    æĺ¥è¿IJ
    0.18
    æĸ°çļĦä¸Ģå¹´
    0.17
    Activations Density 0.314%

    No Known Activations