© 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. 51632
    Prev
    Next
    INDEX
    Explanations

    possessive 'whose' followed by noun

    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
    æĸ°ä¸ĸ纪
    -0.09
    å½ĵåľ°çļĦ
    -0.09
    æĸ¯é¡¿
    -0.09
    /or
    -0.09
    ero
    -0.08
    å¯ĦãģĽ
    -0.08
    those
    -0.08
    \_
    -0.08
    èį·
    -0.08
    åŃ¦æł¡çļĦ
    -0.08
    POSITIVE LOGITS
    soever
    0.13
    elves
    0.13
    opers
    0.10
    çī¹çĤ¹æĺ¯
    0.10
     own
    0.10
    THING
    0.10
    å¤ļãģı
    0.09
    ought
    0.09
    éĿ¢è²Į
    0.09
    forth
    0.09
    Activations Density 0.019%

    No Known Activations