© 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. 33373
    Prev
    Next
    INDEX
    Explanations

    found that

    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
    èģĶç³»æĸ¹å¼ı
    -0.09
    并åıij
    -0.09
    åĦ¿
    -0.09
    æį®äºĨ解
    -0.09
    æŃ£åĢ¼
    -0.09
    éĿł
    -0.08
    lices
    -0.08
    æĪij认为
    -0.08
    á»Ĭ
    -0.08
    enz
    -0.08
    POSITIVE LOGITS
    æľīç§į
    0.10
    adt
    0.09
    common
    0.09
    èĨĽ
    0.08
    è¡·
    0.08
    anding
    0.08
    åŃ£åIJİ
    0.08
    è¶Ĭå¤ļ
    0.08
    èĨº
    0.08
     rooting
    0.08
    Activations Density 0.077%

    No Known Activations