© 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. 62900
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb or auxiliary

    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
    åıªèĥ½è¯´
    -0.10
    ä¸įæĺİ
    -0.10
    ä¸įåħį
    -0.10
     McInt
    -0.09
    æĪij们就
    -0.09
     ÙĦدÙĬÙĨا
    -0.09
    迫使
    -0.09
    èĩªå®¶
    -0.09
    èĩªèº«çļĦ
    -0.09
    æĪij们çļĦ
    -0.09
    POSITIVE LOGITS
    åıĬåħ¶
    0.10
    è¿Ļä¹Īåģļ
    0.09
    /her
    0.09
    ees
    0.09
    ocation
    0.08
    åľ¨æĦı
    0.08
    ä¸Ģ个éĩįè¦ģ
    0.08
    åħ¨æĹ¥
    0.08
     Packing
    0.08
    åĭ¤
    0.08
    Activations Density 0.065%

    No Known Activations