© 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. 20812
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by common nouns

    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
    çľ¼éĩĮ
    -0.09
    滨海
    -0.09
    è´±
    -0.08
     lẽ
    -0.08
    Interior
    -0.08
    人å±ħ
    -0.08
    SYNC
    -0.08
     inertia
    -0.08
    ä»ĸä»¬åľ¨
    -0.08
     discre
    -0.08
    POSITIVE LOGITS
    éĢĢ
    0.10
    åķĨä¸ļ
    0.10
    å¼Ħå¾Ĺ
    0.10
    éĶĢæ¯ģ
    0.10
    èªįèŃĺ
    0.09
    гла
    0.09
    ç¾½æ¯Ľ
    0.09
    Commercial
    0.09
     commerc
    0.09
    çĥŃéĹ¹
    0.09
    Activations Density 0.003%

    No Known Activations