© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20827
    Prev
    Next
    INDEX
    Explanations

    treatment efficacy studies

    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
    足足
    -0.09
    äºİæĺ¯
    -0.08
    Âł
    -0.08
     El
    -0.08
    åIJIJ
    -0.07
    å½¢æĪIJäºĨ
    -0.07
    iced
    -0.07
    çİŁ
    -0.07
    åı¬
    -0.07
    mers
    -0.07
    POSITIVE LOGITS
    æľªæĿ¥åıijå±ķ
    0.10
    èĬ±å¼Ģ
    0.10
    æ¯ı人
    0.09
    makt
    0.09
    -Sah
    0.09
    å°ıäºĭ
    0.09
    ä¸ŃæľŁ
    0.09
    对çħ§æ£ĢæŁ¥
    0.09
    åįİ举
    0.09
    peare
    0.09
    Activations Density 0.128%

    No Known Activations