© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63735
    Prev
    Next
    INDEX
    Explanations

    possessive determiner 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
    触åıij
    -0.09
    æ»ŀåIJİ
    -0.09
     triggers
    -0.09
    çļĦåľ°æŃ¥
    -0.09
    让人们
    -0.08
    ä¹ĥ
    -0.08
    é¢Ĭ
    -0.08
    lsa
    -0.08
    èµ°äºĨ
    -0.08
    å¿łå®ŀ
    -0.08
    POSITIVE LOGITS
    addy
    0.10
    master
    0.09
    è·¯ä¸Ĭ
    0.09
    wy
    0.09
    åħ±åIJĮ
    0.08
    té
    0.08
    oute
    0.08
    å¤įæĿĤ
    0.08
    Pitch
    0.08
    ç»ıåİĨ
    0.08
    Activations Density 0.063%

    No Known Activations