© 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. 27613
    Prev
    Next
    INDEX
    Explanations

    bathroom and recreational facilities

    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
    æĹłçŁ¥
    -0.10
    borg
    -0.09
    èĢĮçİ°åľ¨
    -0.09
    顼
    -0.09
    å°Ĩèĩªå·±çļĦ
    -0.08
     sag
    -0.08
    ÑĢод
    -0.08
    æľĢåIJİä¸Ģ个
    -0.08
    çļĦ人æĿ¥è¯´
    -0.08
    俪
    -0.08
    POSITIVE LOGITS
    çŃīä¸Ģæī¹
    0.09
    åĴĮæĶ¯æĮģ
    0.09
    çŃīçī¹çĤ¹
    0.09
    æ¯ıä½į
    0.09
    称ä¹ĭ
    0.08
    箧
    0.08
    åľ¨åĨħçļĦ
    0.08
    æľ¬ç«Ļ
    0.08
    æĺ¯çľŁçļĦ
    0.08
    åı¤èĢģ
    0.08
    Activations Density 0.238%

    No Known Activations