© 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. 10705
    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
     Burg
    -0.09
    æĴŃ
    -0.08
    鼷
    -0.08
    åĽĽå¤§
    -0.08
    åºŁå¼ĥ
    -0.08
    zell
    -0.08
    chia
    -0.08
    رÙĥ
    -0.08
    享
    -0.07
    ä¸ī大
    -0.07
    POSITIVE LOGITS
    éķľåŃIJ
    0.12
    çģµæĦŁ
    0.11
    æĹłå½¢
    0.10
    æĮĩåįĹ
    0.10
    åĶ¯ä¸ĢçļĦ
    0.10
    äºĨæĪijçļĦ
    0.10
    éĩįä¸Ń
    0.10
    æħ°
    0.10
    éĥĽ
    0.10
    abler
    0.10
    Activations Density 0.068%

    No Known Activations