© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38281
    Prev
    Next
    INDEX
    Explanations

    excuse, explain, justify

    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¸Ģæŀ¶
    -0.10
    лег
    -0.10
    éĿ©
    -0.10
    çļĦéģĵçIJĨ
    -0.10
    å·¥åľ°
    -0.10
    åľ°éģĵ
    -0.09
    ä¸įæĺİçĻ½
    -0.09
    é¢ĨæĤŁ
    -0.09
    æĬķè¯ī
    -0.09
    åģĩæĹ¥
    -0.09
    POSITIVE LOGITS
    æİī
    0.10
    è¡Į为
    0.08
    åŃĺåľ¨çļĦ
    0.08
    otes
    0.08
    æİīäºĨ
    0.08
    ä¸įéĢļ
    0.08
    åĪĹåħ¥
    0.08
    å¼łè´´
    0.07
    æĹ·
    0.07
    elu
    0.07
    Activations Density 0.039%

    No Known Activations