© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37479
    Prev
    Next
    INDEX
    Explanations

    scenery and views

    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
    åľ¨å¤ĸ
    -0.10
    èĢĹ
    -0.09
    åľ¨ç½ij绾ä¸Ĭ
    -0.09
    loat
    -0.08
     reap
    -0.08
    .Inner
    -0.08
    обÑĢа
    -0.08
     вÑĢемен
    -0.08
    æİĩ
    -0.08
    åľ¨åŃ¦æł¡
    -0.08
    POSITIVE LOGITS
    æĤŁ
    0.11
    å®ĮåĸĦçļĦ
    0.10
    è¿Ļä¸ªåľ°æĸ¹
    0.10
    æ°ĽåĽ´
    0.10
    çĶŁæ´»çݯå¢ĥ
    0.10
    交éĢļ
    0.10
    primitive
    0.10
    ç¦Ģ
    0.10
    ç¾İ丽çļĦ
    0.10
    èµĦæºIJä¼ĺåĬ¿
    0.10
    Activations Density 0.088%

    No Known Activations