© 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. 23393
    Prev
    Next
    INDEX
    Explanations

    come and

    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
    éĢ¢
    -0.09
    åħļåĴĮæĶ¿åºľ
    -0.08
    常æĢģ
    -0.08
    ä¸įåħ¬å¹³
    -0.08
    å·į
    -0.08
    åĽ½æĥħ
    -0.08
    æĥ³äºĨ
    -0.08
    ç»Ī究
    -0.08
    è¦ģçľĭ
    -0.08
    æİ£
    -0.08
    POSITIVE LOGITS
    æĪij们ä¸Ģèµ·
    0.11
    åıĤä¸İåĪ°
    0.10
    åĩĢåĮĸ
    0.10
    交æµģ
    0.09
    ä¸ºçĽ®çļĦ
    0.09
    nton
    0.09
    ç¡IJ
    0.09
    å³Ĵ
    0.09
    agner
    0.09
    çļĪ
    0.09
    Activations Density 0.006%

    No Known Activations