© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38148
    Prev
    Next
    INDEX
    Explanations

    other than

    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
    oux
    -0.10
    aign
    -0.10
    åĪ¥äºº
    -0.10
    allon
    -0.09
    keit
    -0.09
    æĹłæķ°æ¬¡
    -0.09
    ê¼´
    -0.09
     дÑĢÑĥгиÑħ
    -0.09
    éĿŀ常å¤ļ
    -0.09
    广大群ä¼Ĺ
    -0.09
    POSITIVE LOGITS
    world
    0.09
    ç«ĭå¿Ĺ
    0.08
    æ¯į
    0.08
    land
    0.08
    æĪijåĴĮ
    0.08
    wd
    0.08
    (_:
    0.08
    vsp
    0.08
    äºĨ解
    0.08
    ippy
    0.07
    Activations Density 0.003%

    No Known Activations