© 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. 64084
    Prev
    Next
    INDEX
    Explanations

    pronouns and possessives

    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
    Negative Logits
    æĻŁ
    -0.08
    illon
    -0.08
     обоÑĢ
    -0.08
    çķĽ
    -0.08
    èĢĥå¯Ł
    -0.08
    åĪĥ
    -0.08
    wish
    -0.08
    æ¡´
    -0.08
    ette
    -0.08
    éĿ©
    -0.08
    POSITIVE LOGITS
    å±ŀäºİèĩªå·±
    0.13
    åģļ人
    0.11
    æľ¬äºº
    0.10
    è¿Ļ个人
    0.10
    äººæł¼
    0.10
    æ¸į
    0.10
    æį¢äºĨ
    0.10
     ÑģебÑı
    0.09
     Ñģобой
    0.09
    常æĢģ
    0.09
    Activations Density 0.062%

    No Known Activations