© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52100
    Prev
    Next
    INDEX
    Explanations

    Tic Tac Toe, Solitaire, Sudoku, online games

    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
    ised
    -0.09
    afe
    -0.08
    æīĢæıIJä¾Ľ
    -0.08
    ized
    -0.07
    ink
    -0.07
    çģ«æĺŁ
    -0.07
    wallet
    -0.07
    åĴĭ
    -0.07
    æĮīè§Ħå®ļ
    -0.07
    æģ£
    -0.07
    POSITIVE LOGITS
    -like
    0.11
    olis
    0.10
    大æĪĺ
    0.09
    礼åĵģ
    0.09
    ãĤ·ãĥª
    0.09
    ìĪľ
    0.09
    å¼ıçļĦ
    0.09
    -style
    0.09
    tolua
    0.09
    åħļæĶ¿
    0.09
    Activations Density 0.048%

    No Known Activations