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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18280
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    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
    éľİ
    -0.11
    对æĸ¹
    -0.11
    æľ¬ç½ij
    -0.11
    èĩªèº«çļĦ
    -0.11
    èĩªå·±çļĦ
    -0.10
    å°įæĸ¹
    -0.10
    .pg
    -0.09
    人家
    -0.09
    opot
    -0.09
    æĺ¶
    -0.09
    POSITIVE LOGITS
    encial
    0.08
    ä»Ģä¹Īåij¢
    0.08
    té
    0.08
    urning
    0.08
     miss
    0.08
    æ´¾
    0.08
    sing
    0.07
    (STD
    0.07
    å¼±
    0.07
    åį«çĶŁéĹ´
    0.07
    Activations Density 0.082%

    No Known Activations