© 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. 50025
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by 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
    à¹Ģà¸Ĥา
    -0.12
    缸åħ³
    -0.11
    缸åħ³äººåijĺ
    -0.10
    éĤ£ç§į
    -0.10
    为ä¸ŃåĽ½
    -0.09
    åīįæıIJ
    -0.09
    åij³éģĵ
    -0.09
    è°Ĵ
    -0.09
    erp
    -0.09
    uj
    -0.09
    POSITIVE LOGITS
     sorts
    0.12
    zelf
    0.10
    åı¯è°ĵæĺ¯
    0.09
    ä¸İåħ¶
    0.08
    losures
    0.08
     predecessors
    0.08
    æĺ¯çľŁçļĦ
    0.08
     renown
    0.08
    "|
    0.08
    /on
    0.08
    Activations Density 0.105%

    No Known Activations