© 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. 63775
    Prev
    Next
    INDEX
    Explanations

    solar phenomena and astronomical terms

    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
    çľ¼ä¸Ń
    -0.10
    æĥħæĦŁ
    -0.10
     пов
    -0.10
     concentr
    -0.09
    å¿ĥ缮ä¸Ń
    -0.09
    /fixtures
    -0.09
    æģļ
    -0.09
    ator
    -0.09
    æĥħæĢĢ
    -0.09
    çľīæ¯Ľ
    -0.09
    POSITIVE LOGITS
     halo
    0.11
    è§ĦèĮĥåĮĸ
    0.09
     Vul
    0.09
    鸡
    0.09
    çŃļ
    0.09
     HOT
    0.09
     mist
    0.09
    ðŁĶ¥
    0.08
    æłĩåĩĨåĮĸ
    0.08
    INI
    0.08
    Activations Density 0.066%

    No Known Activations