© 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. 50393
    Prev
    Next
    INDEX
    Explanations

    initials followed by words

    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
    ichel
    -0.08
    ä¸Ģå±Ĥ
    -0.08
    aire
    -0.08
    éħįå¥Ĺ
    -0.08
    inate
    -0.08
    lev
    -0.07
    æŀ¢çº½
    -0.07
    ä¸Ģ头
    -0.07
    /or
    -0.07
    eny
    -0.07
    POSITIVE LOGITS
    çľ¼éĩĮ
    0.10
    è¾ı
    0.09
    éĽĨåĽ¢æĹĹä¸ĭ
    0.09
    è°Ĭ
    0.09
    éĽĨåĽ¢
    0.08
    ä½ĵåĪ¶æĶ¹éĿ©
    0.08
    éĶĿ
    0.08
    !--
    0.08
    彩èĻ¹
    0.08
     skirts
    0.08
    Activations Density 0.278%

    No Known Activations