© 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. 35924
    Prev
    Next
    INDEX
    Explanations

    's possessives after names and abbreviations

    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
    ç»ĵ
    -0.10
    èĤĵ
    -0.09
    ilet
    -0.09
    uParam
    -0.09
    满æĢĢ
    -0.08
    ä¸ŃåŃĺåľ¨çļĦ
    -0.08
    åįģåĪĨéĩįè¦ģ
    -0.08
    arde
    -0.08
    ULONG
    -0.08
    .addValue
    -0.08
    POSITIVE LOGITS
    's
    0.19
    ’s
    0.18
    çļĦ产åĵģ
    0.15
    çļĦä¸ľè¥¿
    0.14
    çļĦå¿ĥ
    0.14
    们çļĦ
    0.13
    ìĿĺ
    0.13
    åĢij
    0.12
    çļĦæľĭåıĭ
    0.12
    çļĦéĹ®é¢ĺ
    0.12
    Activations Density 0.127%

    No Known Activations