© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59128
    Prev
    Next
    INDEX
    Explanations

    proper nouns after apostrophe

    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
    æ¯ķ
    -0.09
    åĩºåħ¥
    -0.09
    ingu
    -0.09
    ç³ľ
    -0.08
    çłģ
    -0.08
    å¥ĸåĬ±
    -0.08
    è·Ĺ
    -0.08
    é£Ł
    -0.08
    DED
    -0.08
    fast
    -0.08
    POSITIVE LOGITS
    éĻĪè¿°
    0.11
    å¯¹æľªæĿ¥
    0.09
    ogie
    0.09
    æľ¬åħ¬åı¸
    0.09
    æŀ¯
    0.09
    ä¿¡æģ¯æĬ«éľ²
    0.09
    åĻ¤
    0.09
    пал
    0.09
    _BINDING
    0.09
    frei
    0.09
    Activations Density 0.063%

    No Known Activations