© 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. 60549
    Prev
    Next
    INDEX
    Explanations

    low light 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
    çĶ³
    -0.11
    edi
    -0.09
    æīª
    -0.09
    çĩİ
    -0.09
    é¢ĸ
    -0.09
    çĶ³æĬ¥
    -0.08
    éĨ®
    -0.08
    _PRINTF
    -0.08
    Ñī
    -0.08
    fare
    -0.08
    POSITIVE LOGITS
    顺çĿĢ
    0.08
     sweating
    0.08
     sweat
    0.08
     complimentary
    0.08
     charge
    0.08
    è´£ç¼ĸ
    0.08
    æ°ijçĶŁ
    0.08
    è·Ĥ
    0.08
    èĢģ人
    0.08
     dim
    0.08
    Activations Density 0.057%

    No Known Activations