© 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. 29925
    Prev
    Next
    INDEX
    Explanations

    the followed by technical terms

    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
    çĴĭ
    -0.11
    æ¢Ń
    -0.10
    administration
    -0.09
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.09
    为主é¢ĺ
    -0.09
    çļĦåĪ°æĿ¥
    -0.09
    主è§Ĥ
    -0.09
    æĮĿ
    -0.09
    æĹĥ
    -0.09
    âľª
    -0.09
    POSITIVE LOGITS
    æĥħåĨµ
    0.09
     casualty
    0.09
    å´¤
    0.08
    åij¨åĽ´çļĦ
    0.08
    ÑĢаг
    0.08
    æľīåħ³è§Ħå®ļ
    0.08
    æķĮ
    0.08
     íķŃ
    0.08
    ä»ĸ们éĥ½
    0.08
    olders
    0.08
    Activations Density 0.168%

    No Known Activations