© 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. 64113
    Prev
    Next
    INDEX
    Explanations

    motion and force

    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
    Negative Logits
    ä¸ĭæĿ¥
    -0.09
    us
    -0.09
    å¯Ĩ
    -0.08
    åijĹ
    -0.08
    èħ±
    -0.08
    ä¸ĭæĿ¥çļĦ
    -0.08
    éĶ¦ç»£
    -0.08
    ç¥Ľ
    -0.08
    sink
    -0.08
    å¯Į
    -0.08
    POSITIVE LOGITS
    å¼¹
    0.11
    ä¸Ģç¬Ķ
    0.10
    æĬĽ
    0.10
     báºŃt
    0.10
    蹿
    0.09
    è·³è·ĥ
    0.09
     trần
    0.09
     Ñĩа
    0.09
    _fragment
    0.09
    èĦ±ç¦»
    0.09
    Activations Density 0.041%

    No Known Activations