© 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. 56438
    Prev
    Next
    INDEX
    Explanations

    comparing or relating to

    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
    epar
    -0.10
    åģľ
    -0.10
    æĢ»çļĦ
    -0.09
    æĪĸå¤ļæĪĸå°ij
    -0.09
    éĥ½ä¸įçŁ¥éģĵ
    -0.09
    è¦ģä¹Ī
    -0.09
    缴æĴŃéĹ´
    -0.08
     главное
    -0.08
    æ±°
    -0.08
    好å¥ĩ
    -0.08
    POSITIVE LOGITS
    è¿Ļ个è¯į
    0.08
    趱
    0.08
    stry
    0.08
    è¿Ļå¥Ĺ
    0.08
    abby
    0.08
    è¿ĻæĶ¯
    0.08
    ắm
    0.08
    consum
    0.08
    ëĤ¼
    0.08
    erah
    0.08
    Activations Density 0.086%

    No Known Activations