© 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. 61953
    Prev
    Next
    INDEX
    Explanations

    visualization and information

    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
    é«ĺæ½®
    -0.09
    æ»´
    -0.09
    æĬĬèĩªå·±
    -0.08
    å°Ĩèĩªå·±çļĦ
    -0.08
    uju
    -0.08
    讫
    -0.08
    æī¾ä¸įåĪ°
    -0.08
    å¢ŀé«ĺ
    -0.08
    ä¸į对
    -0.08
    hl
    -0.08
    POSITIVE LOGITS
    精确
    0.12
    åĩĨç¡®
    0.10
    ç²¾åĩĨ
    0.10
    åħ¨éĿ¢
    0.10
    详ç»ĨçļĦ
    0.10
    ç»Ĩèĩ´
    0.10
    åīįæīĢæľªæľī
    0.09
    详ç»Ĩ
    0.09
    å®ŀæŶ
    0.09
    ÐŁÐ¾Ð´ÑĢоб
    0.09
    Activations Density 0.508%

    No Known Activations