© 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. 59268
    Prev
    Next
    INDEX
    Explanations

    climate and cold

    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
    æĴĴ
    -0.11
    é¢Ĩ
    -0.09
    æªĢ
    -0.09
    森
    -0.09
    ä¸īåŃ£åº¦
    -0.09
    ä¸įåIJ«
    -0.08
    è½½
    -0.08
    éĴ±
    -0.08
    ole
    -0.08
    çļĦåİĭåĬĽ
    -0.08
    POSITIVE LOGITS
    åĨ»
    0.13
    å¯Ĵ
    0.12
     frost
    0.11
    æļĸæ°Ķ
    0.11
    éľľ
    0.11
    loo
    0.11
    .freeze
    0.11
    freeze
    0.10
    æĺ¯ä»Ģä¹Īåij¢
    0.10
    çī¹æĸ¯
    0.10
    Activations Density 0.049%

    No Known Activations