© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20241
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun followed by noun

    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
    ä¼į
    -0.08
     Brotherhood
    -0.08
     mes
    -0.08
    åħ¸
    -0.08
    ervas
    -0.08
    æ¯ıä¸Ģ
    -0.08
     Kapoor
    -0.08
    letic
    -0.08
    æ¡Ĩ
    -0.07
    ä¸ģ
    -0.07
    POSITIVE LOGITS
    åIJį为
    0.12
    èĩªå·±åĸľæ¬¢
    0.11
    èijĹåIJįçļĦ
    0.10
    çIJĨæĥ³çļĦ
    0.10
    åĩºèī²
    0.10
    类似
    0.10
    åľ°å¸¦
    0.09
    类似äºİ
    0.09
    åIJįåı«
    0.09
    ç³»åĪĹ
    0.09
    Activations Density 0.096%

    No Known Activations