© 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. 54896
    Prev
    Next
    INDEX
    Explanations

    walls, sides, interface, periphery

    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
    èĽĭ
    -0.08
    ç¹ģå¿Ļ
    -0.08
    人家
    -0.08
    ickle
    -0.08
    æĸ½è¡Į
    -0.08
    饱
    -0.08
    ettes
    -0.08
    åħ·ä½ĵæĥħåĨµ
    -0.08
     sever
    -0.08
    ä¸Ńåįİ
    -0.08
    POSITIVE LOGITS
    æĿµ
    0.09
    åĴ¨
    0.09
    褥
    0.09
    æĪIJ交
    0.09
    å¾¼
    0.08
    æ¡Į
    0.08
    íĻĺ
    0.08
    Dispatch
    0.08
    ody
    0.08
    派人
    0.08
    Activations Density 0.041%

    No Known Activations