© 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. 2892
    Prev
    Next
    INDEX
    Explanations

    programming languages

    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
    æĶ¾å¼Ģ
    -0.10
    稿
    -0.10
    è¿Ļç¯ĩ
    -0.09
    ä¿®æŃ£
    -0.09
    ç²¾åĵģ
    -0.09
    éĩįè¦ģåĨħ容
    -0.09
    ç©´
    -0.09
    稿件
    -0.09
    ุม
    -0.08
    Adobe
    -0.08
    POSITIVE LOGITS
     languages
    0.16
    languages
    0.15
    è¯Ńè¨Ģ
    0.14
     Languages
    0.13
     language
    0.12
     ÑıзÑĭк
    0.12
    -language
    0.12
     lang
    0.11
    (lang
    0.11
    lang
    0.11
    Activations Density 0.551%

    No Known Activations