© 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. 32848
    Prev
    Next
    INDEX
    Explanations

    stop something

    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
    ä¸įéĶĪ
    -0.10
    è°ģçŁ¥éģĵ
    -0.10
    oping
    -0.09
    åIJİæĿ¥
    -0.09
    loth
    -0.09
    verting
    -0.09
     ÐĹна
    -0.09
    LEC
    -0.09
    åĢĴåľ¨
    -0.09
    çŁ¥éģĵäºĨ
    -0.09
    POSITIVE LOGITS
    æĢĿèĢĥ
    0.09
     hẳn
    0.09
    樵
    0.09
    äºĨä»ĸçļĦ
    0.08
    /remove
    0.08
    å¾Ģå¤ĸ
    0.08
    rek
    0.08
    æľįåĬ¡äºİ
    0.08
    reck
    0.08
    äºĨæĪijçļĦ
    0.08
    Activations Density 0.014%

    No Known Activations