© 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. 52379
    Prev
    Next
    INDEX
    Explanations

    examples of categories

    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
    æľĢçĪ±
    -0.09
    pling
    -0.08
    dash
    -0.08
    éĿŀ常好
    -0.08
    boxing
    -0.08
    ynch
    -0.08
    Ń
    -0.08
    .setSelected
    -0.08
    ä¸įåı¯èĥ½
    -0.08
    ntag
    -0.08
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.11
    ä½Ĩä¸įéĻIJ
    0.11
    以ä¸ĭåĩłä¸ª
    0.10
    ä¼ģä¸ļåĴĮ
    0.10
    管çIJĨåĴĮ
    0.09
    reh
    0.09
    è±ķ
    0.09
    ä¸Ģ个æĺ¯
    0.09
    éĤ£äºĽ
    0.09
    OMEM
    0.09
    Activations Density 0.061%

    No Known Activations