© 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. 10766
    Prev
    Next
    INDEX
    Explanations

    natural products and compounds

    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
    è¿ĩ硬
    -0.09
    è¿ĻäºĽéĹ®é¢ĺ
    -0.09
    cup
    -0.09
    ä¹ħäºĨ
    -0.08
     imaginary
    -0.08
    imag
    -0.08
    åĶ¤
    -0.08
    èĩ´å¯Į
    -0.08
     SK
    -0.08
    ric
    -0.08
    POSITIVE LOGITS
    èĩªçĦ¶çķĮ
    0.14
     naturally
    0.12
    åŃĺåľ¨äºİ
    0.12
    ä½ĵåĨħ
    0.12
    åŃĺéĩı
    0.11
    æĻ®éģįåŃĺåľ¨
    0.10
    åĵªéĩĮ
    0.10
     à¹Ĩ
    0.10
    大èĩªçĦ¶
    0.10
    çݯå¢ĥä¸Ń
    0.10
    Activations Density 0.479%

    No Known Activations