© 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. 17554
    Prev
    Next
    INDEX
    Explanations

    numbers and next words

    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
    opus
    -0.08
    æĭ´
    -0.08
    磨
    -0.08
    å¤ļå¹´åīį
    -0.08
    UCT
    -0.08
    ipe
    -0.08
    aths
    -0.08
    å¸ĤåľºåĮĸ
    -0.08
     lúc
    -0.08
    ile
    -0.08
    POSITIVE LOGITS
    ä¸ĭ次
    0.13
    ä¸ĭä¸Ģ
    0.13
    åŃ¦æľŁ
    0.12
    æľªæĿ¥çļĦ
    0.12
    è¿Ļä¸Ģ次
    0.12
    年度
    0.11
    åIJİç»Ń
    0.11
    ä¸ĭä¸Ģ代
    0.11
    ä¸ĭä¸Ģ个
    0.11
    ä¸ĢæľŁ
    0.10
    Activations Density 0.154%

    No Known Activations