© 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. 3626
    Prev
    Next
    INDEX
    Explanations

    at least

    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
    è¦ģ说
    -0.10
    ä¸ĢçĤ¹ä¹Łä¸į
    -0.09
    ãģĨãģ¡
    -0.08
    ä¸įå®ī
    -0.08
    åıĺå½¢
    -0.08
     Reid
    -0.08
    venture
    -0.08
    å©Ĩ
    -0.07
    LO
    -0.07
    NY
    -0.07
    POSITIVE LOGITS
    ÑĢаÐ
    0.11
    ESA
    0.10
    /AFP
    0.10
    eds
    0.10
    çŁ¥éģĵèĩªå·±
    0.09
    åģļäºĭ
    0.09
    ãģĿãģĵãģ«
    0.09
    uger
    0.09
    ç²²
    0.09
    ç®Ĺæĺ¯
    0.09
    Activations Density 0.009%

    No Known Activations