© 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. 24285
    Prev
    Next
    INDEX
    Explanations

    relativity and physics formulas

    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
    usty
    -0.09
    ync
    -0.09
     оÑĤз
    -0.09
    碰æĴŀ
    -0.09
    _CSS
    -0.09
    çĶ¥
    -0.09
    eldom
    -0.09
    è¡°èĢģ
    -0.08
     Lod
    -0.08
    忤
    -0.08
    POSITIVE LOGITS
    ä¸Ģçľĭ
    0.09
    åįģéĩĮ
    0.08
    涵
    0.08
    åįĩéĻį
    0.08
    èĿł
    0.08
    å¯ĮåIJ«
    0.08
    çľīæ¯Ľ
    0.08
    åįĩ
    0.08
    èµ·ä¼ı
    0.08
    ç¦ģå¿Į
    0.08
    Activations Density 0.245%

    No Known Activations