© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 16630
    Prev
    Next
    INDEX
    Explanations

    valley before state or california

    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
    Negative Logits
     именно
    -0.09
    /conf
    -0.09
    äºĶå®ĺ
    -0.09
     пÑĢаво
    -0.08
    itchen
    -0.08
    èµ°åĩº
    -0.08
    æŁ¬
    -0.08
    ç®±
    -0.08
     BTN
    -0.08
     Goodman
    -0.08
    POSITIVE LOGITS
     Vaugh
    0.10
    åĬ¨æīĭ
    0.09
    åľ°åĿª
    0.09
    AGMA
    0.09
    æĿijéķĩ
    0.08
    æ»Ł
    0.08
    æĿŃ
    0.08
    涮
    0.08
    讪
    0.08
    ä¼ģä¸ļåĴĮ
    0.08
    Activations Density 0.114%

    No Known Activations