© 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. 9154
    Prev
    Next
    INDEX
    Explanations

    placeholder characters

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    trag
    -0.08
    è·º
    -0.08
    ä¸įäºĨ
    -0.08
    /right
    -0.08
    s
    -0.08
    åľ¨åĨħçļĦ
    -0.08
    reh
    -0.07
    tant
    -0.07
    åĴĮåľ°åĮº
    -0.07
    POSITIVE LOGITS
    æĶ¯çIJĥéĺŁ
    0.09
    ç«¿
    0.09
    crypt
    0.09
    壤
    0.09
    침
    0.09
    ienen
    0.09
    dio
    0.09
    éĹ®è¯¢
    0.09
    åŃIJéĩĮ
    0.08
    鼷æĸ¯
    0.08
    Activations Density 0.080%

    No Known Activations