© 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. 39527
    Prev
    Next
    INDEX
    Explanations

    can / could / may

    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
    ulate
    -0.11
    æķ¢
    -0.10
    æŃ£åĽłä¸º
    -0.09
    åı¯ä»¥ä½¿
    -0.09
    å¾Īæľī
    -0.09
    éĩľ
    -0.09
    æ§į
    -0.09
    åĨįæĿ¥
    -0.09
    mob
    -0.08
    é«ĺå³°
    -0.08
    POSITIVE LOGITS
    æĹ©æĹ¥
    0.11
    æĽ´å¥½åľ°
    0.10
    å°½æĹ©
    0.09
    çķĻä½ı
    0.09
    æĽ´å¥½çļĦ
    0.09
     ÑħоÑĤÑĮ
    0.09
    ä½ĵä¼ļ
    0.08
    尽快
    0.08
     better
    0.08
     understanding
    0.08
    Activations Density 0.045%

    No Known Activations