© 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. 36243
    Prev
    Next
    INDEX
    Explanations

    Big Ten Conference, awards, school records

    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
    æīĢåľ¨çļĦ
    -0.09
     foul
    -0.08
    ITA
    -0.08
    ultan
    -0.08
    广å·ŀå¸Ĥ
    -0.08
    èķĥ
    -0.08
    Returned
    -0.07
    æĪ¿ä¸ľ
    -0.07
    getData
    -0.07
    deo
    -0.07
    POSITIVE LOGITS
    æķŀå¼Ģ
    0.10
    æĪIJç«ĭ以æĿ¥
    0.09
    à¸Ļาม
    0.09
    åĵĤ
    0.09
    .opensource
    0.09
    ãĥ³ãĥĪ
    0.09
    ಡ
    0.09
    xit
    0.09
    èĪŀåı°ä¸Ĭ
    0.09
    çĮĹ
    0.09
    Activations Density 0.005%

    No Known Activations