© 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. 37535
    Prev
    Next
    INDEX
    Explanations

    Japanese characters followed by English words

    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
    åĮĸçļĦ
    -0.10
    ieri
    -0.09
    -0.09
    溢
    -0.09
    edm
    -0.09
    ìĿ¸
    -0.08
    çŃīéĥ¨éŨ
    -0.08
    ãģ§ãģĻãģ®ãģ§
    -0.08
    æľ¬èº«çļĦ
    -0.08
     اÙĦÙħشارÙĥØ©
    -0.08
    POSITIVE LOGITS
    éħĮ
    0.10
    迹象
    0.10
    ä¸įå¾Ĺ转载
    0.09
    anus
    0.09
    æł·åŃIJ
    0.09
     ê²ĥ
    0.09
    æŃ£å½ĵ
    0.09
    ãģĵãģ¨ãģ§
    0.09
    ê²ĥ
    0.09
    iona
    0.09
    Activations Density 0.031%

    No Known Activations