© 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. 49691
    Prev
    Next
    INDEX
    Explanations

    your and their followed by nouns

    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
    æīĢæīĢéķ¿
    -0.09
    åįķ车
    -0.09
    æī¾å·¥ä½ľ
    -0.09
    åħ¶æīĢ
    -0.08
    arie
    -0.08
    leÅŁ
    -0.08
    çªĴæģ¯
    -0.08
    eken
    -0.08
    ä»İåݻ年
    -0.08
    .mozilla
    -0.08
    POSITIVE LOGITS
    ä¼ģä¸ļçļĦ
    0.13
    产åĵģçļĦ
    0.11
    è²Į
    0.10
    uchs
    0.09
    åĵģçīĮçļĦ
    0.09
     Boeh
    0.09
     website
    0.09
    ä¼ģä¸ļ
    0.09
     logo
    0.09
    åѦçĶŁçļĦ
    0.09
    Activations Density 0.126%

    No Known Activations