© 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. 60669
    Prev
    Next
    INDEX
    Explanations

    eutrophic conditions

    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
    æĶ¹éĿ©åĪĽæĸ°
    -0.09
    è¡Ĺ
    -0.09
    æ´¾
    -0.08
    oplan
    -0.08
    oid
    -0.08
    åĸĻ
    -0.08
    ä»ĭ
    -0.08
     kostenlose
    -0.08
    æĥ®
    -0.08
    inous
    -0.08
    POSITIVE LOGITS
    åIJĪä¸Ģ
    0.11
    ök
    0.09
    çĵĴ
    0.09
    spo
    0.09
    éĤ£ä¸Ģ
    0.08
    æ·Ģ
    0.08
    èIJ¥åħ»
    0.08
    份
    0.08
    èIJ¥éĢłèī¯å¥½
    0.08
    éĺĻ
    0.08
    Activations Density 0.037%

    No Known Activations