© 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. 51264
    Prev
    Next
    INDEX
    Explanations

    pronoun "it"

    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
    è¿Ļæīįæĺ¯
    -0.10
    éĢļãĤĬ
    -0.10
    è¿Ļæł·ä¸Ģ
    -0.10
    æĸ¯é¡¿
    -0.10
    è¦ģèĢĥèĻij
    -0.10
    åĪ°æľĢåIJİ
    -0.10
    èĩ³æѤ
    -0.10
    è¿ĽæĿ¥
    -0.10
    iously
    -0.09
    è¦ģåģļåĪ°
    -0.09
    POSITIVE LOGITS
    /from
    0.13
     ÙĪعÙĨ
    0.10
    chy
    0.09
     being
    0.08
    endant
    0.08
    /about
    0.08
    /her
    0.08
    é¼ĭ
    0.08
    /on
    0.07
    æĪijæĥ³
    0.07
    Activations Density 0.074%

    No Known Activations