© 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. 62205
    Prev
    Next
    INDEX
    Explanations

    advances in technology and research

    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«ĺæĺĤ
    -0.08
    ç£ĭåķĨ
    -0.08
    аÑģ
    -0.08
    ç§ijåĪĽæĿ¿
    -0.08
    ноп
    -0.08
    å¥Ķæ³¢
    -0.08
    å¢ŀåĢ¼æľįåĬ¡
    -0.08
    ä¸ĵåĪ©
    -0.08
     Swan
    -0.08
    -like
    -0.07
    POSITIVE LOGITS
    è¿Ļæĸ¹éĿ¢
    0.11
    rapid
    0.11
    ìĤ¬íķŃ
    0.10
    è¿ħéĢŁ
    0.10
    _pod
    0.10
     strides
    0.09
    acje
    0.09
    ä¸įå¿į
    0.09
    reich
    0.09
    å¹ħ
    0.09
    Activations Density 0.092%

    No Known Activations