© 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. 6528
    Prev
    Next
    INDEX
    Explanations

    numbers and xml tags

    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
    noinspection
    -0.10
    çīĮ
    -0.10
    ç
    -0.09
    æĹ¶ç©º
    -0.09
    é¦ĸå¯Į
    -0.09
    移éĢģ
    -0.09
    é¢Ļ
    -0.09
    (Board
    -0.09
    æŀľ
    -0.09
    ä¸įç¦ģ
    -0.08
    POSITIVE LOGITS
    èģĶ绾
    0.10
    tas
    0.09
    çĶµè¯Ŀ
    0.08
    èģ¯çµ¡
    0.08
    éİı
    0.08
    åħļé£İ
    0.08
    ioms
    0.08
     ÑĢаÐ
    0.08
    é¾Ļæ³ī
    0.08
    æĸ°åĨł
    0.08
    Activations Density 0.034%

    No Known Activations