© 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. 39730
    Prev
    Next
    INDEX
    Explanations

    phrases starting with 'maybe' or ending with 'should'

    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
    åıijè¨Ģ人
    -0.09
    acos
    -0.09
    æİ©
    -0.09
    æĢħ
    -0.09
    æĹ¥æŃ£å¼ı
    -0.09
    åIJĮæĹ¶ä¹Łæĺ¯
    -0.08
    ä»ĸ认为
    -0.08
    IEL
    -0.08
    åĨĻéģĵ
    -0.08
    elib
    -0.08
    POSITIVE LOGITS
    ãģĭãĤĤãģĹãĤĮãģ¾ãģĽãĤĵãģĮ
    0.11
    ä½ĨæĪij
    0.10
    ä½Ĩæĺ¯æĪij
    0.10
    ä½Ĩæĺ¯å¯¹äºİ
    0.10
    ä½Ĩæĺ¯å¦Ĥæŀľ
    0.09
    ãģĦãģ¾ãģĻãģĮ
    0.09
    è¿ĻæĿ¡
    0.09
    åı¯æĺ¯
    0.09
    ãģ¾ãģĹãģŁãģĮ
    0.09
    ä½Ĩå¦Ĥæŀľ
    0.09
    Activations Density 0.248%

    No Known Activations