© 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. 29720
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and determiners

    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
    山水
    -0.10
     Dad
    -0.08
    ÅĽl
    -0.08
    çIJĨä¼ļ
    -0.07
    åĪ°æĿ¥
    -0.07
    åľ¨è¿Ļ个
    -0.07
    мол
    -0.07
    éģĵçIJĨ
    -0.07
    าà¸Ļ
    -0.07
    ajan
    -0.07
    POSITIVE LOGITS
    ä»ĸçļĦ
    0.23
    èĩªå·±çļĦ
    0.23
    åħ¶
    0.21
     Ñģвоей
    0.21
    她çļĦ
    0.21
     sua
    0.21
     seus
    0.19
    å®ĥçļĦ
    0.19
    ä»ĸ们çļĦ
    0.19
     their
    0.19
    Activations Density 0.611%

    No Known Activations