© 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. 32131
    Prev
    Next
    INDEX
    Explanations

    is followed by evaluative terms

    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
    并ä¸įæĺ¯å¾Ī
    -0.11
    ä¹Łåıªæĺ¯
    -0.11
    ä¸įå°ıçļĦ
    -0.10
     khá
    -0.10
    è¿ĺæĮº
    -0.10
    ä¹Łæ¯Ķè¾ĥ
    -0.10
    ä½Ĩä»ĸ们
    -0.10
    ä¸įæĺ¯å¾Ī
    -0.10
    è¿ĺæĺ¯æ¯Ķè¾ĥ
    -0.10
    æ¯Ķè¾ĥå¤ļ
    -0.10
    POSITIVE LOGITS
    ç®Ģ缴æĺ¯
    0.12
    åłªç§°
    0.10
    ç®Ģ缴
    0.09
     абÑģолÑİÑĤно
    0.09
    æĹłæ¯Ķ
    0.09
     sheer
    0.08
    ç»Ŀ对æĺ¯
    0.08
    ä¸Ģéģį
    0.08
     flaw
    0.08
    å®Įåħ¨æĺ¯
    0.08
    Activations Density 0.131%

    No Known Activations