© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7942
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by owned 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
    è¿ĺèĥ½
    -0.09
    çī¹åĪ«
    -0.08
    åħŃ大
    -0.08
    çİĽä¸½
    -0.07
    Reuse
    -0.07
    å©ļ
    -0.07
    IDES
    -0.07
    ault
    -0.07
    /pdf
    -0.07
    åĨ¯
    -0.07
    POSITIVE LOGITS
    äºĨèĩªå·±çļĦ
    0.11
    éºŁ
    0.10
    èĩªå·±çļĦ
    0.10
    ç³Ł
    0.10
    åIJĦèĩª
    0.10
    éºĴ
    0.10
    ç»ıèIJ¥æ´»åĬ¨
    0.10
    æ¿Ĵ
    0.09
    æĽ´åħ·
    0.09
    orsi
    0.09
    Activations Density 0.058%

    No Known Activations