© 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. 23166
    Prev
    Next
    INDEX
    Explanations

    is followed by a descriptive clause

    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
    åIJĦè¡ĮåIJĦä¸ļ
    -0.10
    并ä¸İ
    -0.09
    èĮ¨
    -0.09
    æ¸ħæ°´
    -0.09
    cludes
    -0.09
     zwar
    -0.09
    åĽºçĦ¶
    -0.09
    æµ·åĨħå¤ĸ
    -0.09
    ä¹Łåıªèĥ½
    -0.09
    ä¹Łæĺ¯ä¸Ģç§į
    -0.08
    POSITIVE LOGITS
    ç«ŁçĦ¶
    0.13
    éĤ£å°±æĺ¯
    0.10
    å±ħçĦ¶
    0.10
    оÑģÑĮ
    0.09
    çݯå¢ĥä¿ĿæĬ¤
    0.09
    otten
    0.09
    åı¦å¤ĸä¸Ģ个
    0.08
    æŁ¥çľĭåħ¨æĸĩ
    0.08
    家ä¼Ļ
    0.08
    女人
    0.08
    Activations Density 0.123%

    No Known Activations