© 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. 60940
    Prev
    Next
    INDEX
    Explanations

    heat stress tolerance

    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
    人æ°ij群ä¼Ĺ
    -0.09
    çĿ¡åīį
    -0.09
    箪
    -0.09
    ç¢į
    -0.09
    æī©å®¹
    -0.09
    çŃ¾ç½²
    -0.08
    æ¢ħèĬ±
    -0.08
    æ°ijä¼Ĺ
    -0.08
    dle
    -0.08
    横åIJij
    -0.08
    POSITIVE LOGITS
    éĤ»
    0.10
    imd
    0.10
     Raider
    0.09
    æĵİ
    0.09
    æİ¨è¿Ł
    0.09
    åĴĢ
    0.09
    è¿Ļ座
    0.08
    /maps
    0.08
    éĶģ
    0.08
    eca
    0.08
    Activations Density 0.161%

    No Known Activations