© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53225
    Prev
    Next
    INDEX
    Explanations

    adverb + past participle

    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
    å¾Īé«ĺåħ´
    -0.09
    æīĢæıIJä¾ĽçļĦ
    -0.09
    tps
    -0.09
    æĪIJçĨŁçļĦ
    -0.09
    马ä¸Ĭå°±
    -0.09
     болÑĮÑĪое
    -0.09
    äºĽè®¸
    -0.08
    æķ´ä¸ªäºº
    -0.08
    åı¯çĸij
    -0.08
    ÑħоÑĤ
    -0.08
    POSITIVE LOGITS
    edBy
    0.10
    ç»ĵåIJĪèµ·æĿ¥
    0.09
    æĪĸèĢħ说
    0.09
    é¹Ħ
    0.09
    eson
    0.09
    以åĨħ
    0.09
     Cummings
    0.09
    èĢĮä¸Ķ
    0.09
    /inet
    0.08
     ÑĢаÑģÑģ
    0.08
    Activations Density 0.159%

    No Known Activations