© 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. 5691
    Prev
    Next
    INDEX
    Explanations

    different perspectives or opinions

    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
    ään
    -0.09
    交éĻħ
    -0.09
    éĨĴæĿ¥
    -0.09
     Berm
    -0.09
    å´ĩæĭľ
    -0.08
    åīį身
    -0.08
     individ
    -0.08
    积累
    -0.08
    gger
    -0.08
    UTH
    -0.08
    POSITIVE LOGITS
    è§ĤçĤ¹
    0.14
    è§Ĩè§Ĵ
    0.12
    .views
    0.11
    åIJ¬åIJ¬
    0.10
    å£°éŁ³
    0.10
     views
    0.10
    ä¸įåIJĮæĦı
    0.10
    çľĭæ³ķ
    0.09
     cla
    0.09
    对ç«ĭ
    0.09
    Activations Density 0.051%

    No Known Activations