© 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. 4679
    Prev
    Next
    INDEX
    Explanations

    career-wise, insistent, forgiveness

    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
    æł¹æį®ä¸įåIJĮ
    -0.10
    åįĥæĸ¹çĻ¾è®¡
    -0.08
    娣
    -0.08
    ä¸ĢéĶ®
    -0.08
    æĸ°è§Ħ
    -0.08
    åĪ°è´¦
    -0.08
    âľħ
    -0.08
    åĤ¨åŃĺ
    -0.07
    ivic
    -0.07
    xEF
    -0.07
    POSITIVE LOGITS
    åĴĮæĬĢæľ¯
    0.10
    èĢģå©Ĩ
    0.10
    Software
    0.10
     Software
    0.10
    弥漫
    0.09
    å¼ĢåıijèĢħ
    0.09
    çļĦæĬĢæľ¯
    0.09
    é¾Į
    0.08
    产åĵģç»ıçIJĨ
    0.08
    è¹Ĥ
    0.08
    Activations Density 1.550%

    No Known Activations