© 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. 18450
    Prev
    Next
    INDEX
    Explanations

    commercial license guidelines

    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
    æ²¥
    -0.09
    acements
    -0.08
    볨
    -0.08
    itsu
    -0.08
    è°Ķ
    -0.08
    .liferay
    -0.08
    æ³®
    -0.08
    undra
    -0.08
    èĭ
    -0.08
    sku
    -0.07
    POSITIVE LOGITS
    管çIJĨæĿ¡ä¾ĭ
    0.11
    管çIJĨåĬŀæ³ķ
    0.11
    çļĦè¦ģæ±Ĥ
    0.09
    æĮĩå¼ķ
    0.09
    管çIJĨåĪ¶åº¦
    0.09
    çļĦè§Ħå®ļ
    0.09
     guidelines
    0.09
    ä¹łæĥ¯
    0.09
    æĮĩ导æĦıè§ģ
    0.08
    æĿ¡ä¾ĭ
    0.08
    Activations Density 0.537%

    No Known Activations