© 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. 35450
    Prev
    Next
    INDEX
    Explanations

    business entities

    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
     Scho
    -0.09
    åĿij
    -0.09
    å¼Ģåı£
    -0.08
    严åİīæīĵåĩ»
    -0.08
    ä»Ģ
    -0.08
    Tweet
    -0.08
    ä¸Ńå°ıåѦ
    -0.08
    骤
    -0.08
    uding
    -0.07
     Farr
    -0.07
    POSITIVE LOGITS
    æĪIJç«ĭäºİ
    0.10
    çݰ代åĮĸ
    0.10
    ä¸ĢæĶ¯
    0.09
    巨头
    0.09
    lify
    0.09
    ÑĮÑİ
    0.09
    è¿ģ
    0.09
    èĢģæĿ¿
    0.09
    åIJįåŃĹ
    0.09
    _JUMP
    0.09
    Activations Density 0.069%

    No Known Activations