© 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. 33831
    Prev
    Next
    INDEX
    Explanations

    lists followed by respectively

    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
    åŃ£
    -0.11
    'options
    -0.10
    æ¹
    -0.10
    æİ¥åľ°æ°Ķ
    -0.10
    zilla
    -0.09
    ìĹł
    -0.09
    .Butter
    -0.09
    è¦ģçľĭ
    -0.09
    HING
    -0.09
    æıª
    -0.09
    POSITIVE LOGITS
     respectively
    0.21
     respective
    0.19
    åĪĨåĪ«ä¸º
    0.14
    åĪĨåĪ«æĺ¯
    0.14
    åĪĨåĪ«
    0.13
    åIJĦèĩª
    0.13
    respect
    0.13
     ÑģооÑĤвеÑĤ
    0.12
    åĪĨåĪ¥
    0.12
    ãģĿãĤĮãģŀãĤĮ
    0.10
    Activations Density 0.019%

    No Known Activations