© 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. 11515
    Prev
    Next
    INDEX
    Explanations

    country

    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
    åIJĮå¿ĥ
    -0.09
    轻轻
    -0.09
    饶
    -0.09
    Ãłng
    -0.09
    _##
    -0.08
    ç¥ľ
    -0.08
    ä¸İåħ¶
    -0.08
    é²į
    -0.08
    æĪIJæŀľè½¬åĮĸ
    -0.08
    è§ī
    -0.08
    POSITIVE LOGITS
    åĽ½å¤ĸ
    0.13
    æľ¬åĽ½
    0.13
    æĺ¯æĪij们
    0.12
    对æĪij们
    0.12
     ìļ°ë¦¬ëĤĺ
    0.12
     country
    0.11
    æĪijçľģ
    0.11
    åĽ½åĨħ
    0.11
    åħ³äºİæĪij们
    0.11
    åľ¨åĽ½å¤ĸ
    0.11
    Activations Density 0.064%

    No Known Activations