© 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. 26428
    Prev
    Next
    INDEX
    Explanations

    people and entities

    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
    rer
    -0.10
    è·ijäºĨ
    -0.09
    ä½İ端
    -0.09
    æĢĽ
    -0.09
    èĢ½
    -0.09
     зани
    -0.09
    arius
    -0.09
    COVERY
    -0.08
    rede
    -0.08
    TextNode
    -0.08
    POSITIVE LOGITS
    's
    0.09
    æĸ¹éĿ¢çļĦ
    0.09
    ä¸ĵå±ŀ
    0.09
    ç³»ç»ŁçļĦ
    0.09
    èĢħçļĦ
    0.09
    ãģ«å¯¾ãģĻãĤĭ
    0.09
    inka
    0.09
    ’s
    0.09
    æīĭä¸ŃçļĦ
    0.09
    PAD
    0.08
    Activations Density 1.118%

    No Known Activations