© 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. 12070
    Prev
    Next
    INDEX
    Explanations

    locations, sites, and buildings

    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
    转åIJij
    -0.10
    飫
    -0.10
    绫
    -0.09
    à²ł
    -0.09
    åłµ
    -0.09
    åĩ¡æľ¬ç½ij
    -0.09
    åŃIJåŃĻ
    -0.09
    婵
    -0.09
    _MOUNT
    -0.09
     fasc
    -0.08
    POSITIVE LOGITS
     Georg
    0.09
    彩èĻ¹
    0.08
    Named
    0.08
    æŀ¶
    0.08
    æķŀ
    0.08
    å¡Į
    0.08
     æŀ
    0.08
    æĺİåªļ
    0.07
    AVE
    0.07
    exe
    0.07
    Activations Density 0.147%

    No Known Activations