© 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. 49465
    Prev
    Next
    INDEX
    Explanations

    writing style guidelines

    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
    主é¢ĺæ´»åĬ¨
    -0.10
    好人
    -0.10
     мн
    -0.09
     ë¬
    -0.09
     Guarantee
    -0.09
    ä¿Ŀè¯ģ
    -0.09
    acts
    -0.09
    ç§Ń
    -0.08
    æīįå¹²
    -0.08
    缺åı£
    -0.08
    POSITIVE LOGITS
    仿
    0.11
    è§ĦèĮĥ
    0.10
    dao
    0.10
    é£İæł¼
    0.09
    éĨ¯
    0.09
    æĮĩå¼ķ
    0.09
     bios
    0.09
     guidelines
    0.09
     style
    0.09
    è§Ħç¨ĭ
    0.09
    Activations Density 0.061%

    No Known Activations