© 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. 34679
    Prev
    Next
    INDEX
    Explanations

    converting into

    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
    çĶŃ
    -0.09
    æĹłè®º
    -0.09
    çĦ¡è«ĸ
    -0.09
    æ¸ł
    -0.09
    à²Ł
    -0.08
    æĹłè®ºæĺ¯
    -0.08
    lsa
    -0.08
    bullet
    -0.08
    è¿Ļæł·çļĦè¯Ŀ
    -0.08
    å¾Ī大
    -0.08
    POSITIVE LOGITS
    ç«ŁçĦ¶
    0.11
    ç«
    0.10
    ç»Į
    0.09
    åķ¬
    0.09
    åıĺæĪIJ
    0.09
    纷
    0.09
    ä¹Łèĥ½
    0.09
     ÑģÑĤал
    0.09
    aines
    0.09
    å±ħçĦ¶
    0.09
    Activations Density 0.099%

    No Known Activations