© 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. 9355
    Prev
    Next
    INDEX
    Explanations

    still is, still here

    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
    ä½łä¼ļåıijçİ°
    -0.10
    æĥ³åĪ°äºĨ
    -0.09
     mừng
    -0.09
    çĭIJ
    -0.09
    çłĶ究表æĺİ
    -0.09
    æĪijçĽ¸ä¿¡
    -0.08
    ç¥ĿæĦ¿
    -0.08
    æĪIJäºĨ
    -0.08
    [last
    -0.08
    orna
    -0.08
    POSITIVE LOGITS
    ä¸įä»ħåı¯ä»¥
    0.11
    ä¸įä»ħ
    0.10
    ä¸įä»ħä»ħ
    0.10
    ä¸įä»ħèĥ½
    0.10
    ä¸įåĥħ
    0.10
    ä¸įä»ħä»ħæĺ¯
    0.10
    ç¡®å®ŀ
    0.10
    ä¸įä»ħæĺ¯
    0.10
     indeed
    0.09
    尽管
    0.09
    Activations Density 0.067%

    No Known Activations