© 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. 18309
    Prev
    Next
    INDEX
    Explanations

    in terms of specific contexts

    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
    ãģĬäºĴ
    -0.11
    çķ¶æĤ¨åľ¨
    -0.09
    ãĥ¡ãĥ¼ãĤ
    -0.09
    使çĶ¨ç¶²è·¯
    -0.08
    ãĤ¢ãĥ¡ãĥª
    -0.08
    ãģĤãĤĬãģĮãģ¨ãģĨãģĶãģĸ
    -0.08
    ãģĿãĤĮãģŀ
    -0.08
    âģĪ
    -0.08
    ãĤ¢ãĤ¤ãĥĨ
    -0.08
    ãģ©ãĤĵãģ©
    -0.08
    POSITIVE LOGITS
    ÙħÙĨاط
    0.19
    ÙħØŃÙĥ
    0.19
    إعÙĦ
    0.19
    Ø£ÙĪضاع
    0.18
    إبد
    0.18
    تشغ
    0.18
    اÙĦتز
    0.18
    ÙħسأÙĦ
    0.17
    ÙħصÙĦ
    0.17
    أجÙĩ
    0.17
    Activations Density 15.078%

    No Known Activations