© 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. 2983
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation

    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
    åıįæŃ£
    -0.08
    æĥħåĨµè¿Ľè¡Į
    -0.08
    åīįæľŁ
    -0.08
    nell
    -0.08
    èī¯æĢ§
    -0.08
    éĻIJ度
    -0.08
    éĽ¹
    -0.08
    èŀįèµĦ
    -0.08
    ç¥
    -0.08
     determin
    -0.08
    POSITIVE LOGITS
    ä¸Ģæł·
    0.13
    åIJĮ樣
    0.11
    ä¸Ģæł·çļĦ
    0.11
    åIJĮæł·
    0.11
    ovy
    0.11
    ä¸Ģ樣
    0.11
    åIJĮæł·çļĦ
    0.10
    icos
    0.09
    ãģ¨åIJĮãģĺ
    0.09
    ä½ķåĨµ
    0.09
    Activations Density 0.187%

    No Known Activations