© 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. 23806
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns before 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
    åĭ¤
    -0.08
    .struct
    -0.08
    ieri
    -0.08
    çijĽ
    -0.08
    amil
    -0.08
    cest
    -0.08
    ä¸Ģå¿ĥ
    -0.08
    ä¸į管æĺ¯
    -0.08
    nation
    -0.08
    Ø¡
    -0.08
    POSITIVE LOGITS
    笥
    0.10
    ologically
    0.10
    èĢ³è¾¹
    0.10
    izontally
    0.10
     own
    0.09
    æĹ©æĻļ
    0.09
    rowned
    0.09
    å¾Īå¤ļæľĭåıĭ
    0.09
     Own
    0.09
    æī¼
    0.09
    Activations Density 0.048%

    No Known Activations