© 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. 5364
    Prev
    Next
    INDEX
    Explanations

    advertising and sponsored content

    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
    åģļå·¥
    -0.10
    à¹ģห
    -0.10
    éĿŀåĩ¡
    -0.09
    riot
    -0.09
     cá»Ń
    -0.09
    åij¸
    -0.09
    碰æĴŀ
    -0.09
    setId
    -0.09
    æł¹æľ¬ä¸į
    -0.09
    èĦ¯
    -0.09
    POSITIVE LOGITS
    广åijĬ
    0.20
     ads
    0.16
    廣åijĬ
    0.15
    ads
    0.14
     advertising
    0.13
     advertisement
    0.13
    Paid
    0.13
    广åijĬæľįåĬ¡
    0.13
     paid
    0.13
     Ads
    0.13
    Activations Density 0.092%

    No Known Activations