© 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. 6363
    Prev
    Next
    INDEX
    Explanations

    sentence terminators

    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
     prop
    -0.08
    æīĢ带æĿ¥çļĦ
    -0.07
    æİĮ
    -0.07
    Prop
    -0.07
    æĹłè®ºæĺ¯åħ¶
    -0.07
    æīĢæıIJä¾ĽçļĦ
    -0.07
     facilities
    -0.07
     specifically
    -0.07
    çŃ¹éĽĨ
    -0.07
    ‘s
    -0.07
    POSITIVE LOGITS
    è¿Ļä¹Łæĺ¯
    0.11
    黾
    0.10
     Äijỡ
    0.10
    è¿Ļéĥ¨åĪĨ
    0.09
    æīĢ以说
    0.09
    æĻ¡
    0.09
    éĹŃçݯ
    0.09
    éļ¾æĢª
    0.09
     поÑįÑĤомÑĥ
    0.09
    ernet
    0.09
    Activations Density 0.058%

    No Known Activations