© 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. 30457
    Prev
    Next
    INDEX
    Explanations

    it's not the

    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
    æľĢå¿«
    -0.11
    åį´ä¸į
    -0.10
    èħ±
    -0.09
    涵
    -0.09
     Lesser
    -0.08
    æľīçĿĢ
    -0.08
    ож
    -0.08
    ÙĤÙĩ
    -0.08
    æĺ¯ä¸įåı¯èĥ½
    -0.08
    lex
    -0.08
    POSITIVE LOGITS
    wel
    0.10
     lack
    0.10
    åĽłç´ł
    0.09
     ÑĦакÑĤоÑĢ
    0.09
    æ¯ģçģŃ
    0.09
    çļĦåĽłç´ł
    0.08
     Lack
    0.08
    edException
    0.08
    士
    0.08
    ãģĵãģ¨ãģĮ
    0.08
    Activations Density 0.096%

    No Known Activations