© 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. 34058
    Prev
    Next
    INDEX
    Explanations

    lists of items

    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
    顶å°ĸ
    -0.09
    aler
    -0.09
    Bow
    -0.09
    ç¼Ł
    -0.09
    说ä¸įåĩº
    -0.08
    ä¸ĸä¸Ĭ
    -0.08
    æ´ĭæ´ĭ
    -0.08
    æĢĿ绪
    -0.08
    alem
    -0.08
    pga
    -0.08
    POSITIVE LOGITS
    äºĮæľŁ
    0.10
    ä¸ĢæľŁ
    0.09
    TM
    0.09
     Advent
    0.08
    åĪĽå§ĭ人
    0.08
    æĺ¯ä¸Ģ家
    0.08
    âĦ¢
    0.08
    http
    0.08
     proprietor
    0.08
    éĤ»
    0.08
    Activations Density 0.501%

    No Known Activations