© 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. 4384
    Prev
    Next
    INDEX
    Explanations

    account registration

    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
    ä¼ļ对
    -0.10
    缮ãģ«
    -0.09
     Wal
    -0.09
    iel
    -0.09
    ä¸į对
    -0.08
    æĹłæ¯Ķ
    -0.08
    ague
    -0.08
    交äºĴ
    -0.08
    BOVE
    -0.08
    ProgressDialog
    -0.08
    POSITIVE LOGITS
    ç¼°
    0.11
    符åIJĪæĿ¡ä»¶
    0.10
    éĻªåIJĮ
    0.10
    æĺ¯è°ģ
    0.09
    çļĦ带é¢Ĩ
    0.09
    åģķ
    0.09
    sf
    0.09
    ç»ĦåĽ¢
    0.09
    å¤ļ人
    0.09
    éĢ£ãĤĮ
    0.09
    Activations Density 0.070%

    No Known Activations