© 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. 59066
    Prev
    Next
    INDEX
    Explanations

    Feynman-Kac equations

    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
    essaging
    -0.09
     dur
    -0.09
    渼
    -0.08
    ICY
    -0.08
    oner
    -0.08
    _CONSTANT
    -0.08
    angers
    -0.08
    inki
    -0.08
    atic
    -0.08
    ANGE
    -0.08
    POSITIVE LOGITS
    å³Ĵ
    0.09
    ä»Ģä¹Īäºĭ
    0.09
    æĪIJ为ä¸ĢåIJį
    0.09
     Ñĥме
    0.09
    æī¾å·¥ä½ľ
    0.09
    èľķ
    0.09
    èĪ¬çļĦ
    0.08
    ä½Ĩä¸įéĻIJ
    0.08
    åĽ½éĻħæľºåľº
    0.08
    èĶ¼
    0.08
    Activations Density 0.001%

    No Known Activations