© 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. 48906
    Prev
    Next
    INDEX
    Explanations

    do so

    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
     gele
    -0.10
    æĶĴ
    -0.10
    erp
    -0.09
    éĢīæĭ
    -0.08
    å«Į
    -0.08
    åıĪ被
    -0.08
    åºĶ该æĢİä¹Ī
    -0.08
    åĿİ
    -0.08
    åıĪ好
    -0.08
     pit
    -0.08
    POSITIVE LOGITS
    è¿Ļæł·åģļ
    0.13
    è¿Ļä¹Īåģļ
    0.11
     thereof
    0.11
    ä¹Łæĺ¯å¦ĤæѤ
    0.11
    åģļæ³ķ
    0.10
    èĥĮæĻ¯
    0.09
     doing
    0.09
    ones
    0.09
     ìĿ´ë¥¼
    0.09
    Doing
    0.09
    Activations Density 0.051%

    No Known Activations