© 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. 688
    Prev
    Next
    INDEX
    Explanations

    HTTPS and SSL security

    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
    ä¸ŃåįİæĸĩåĮĸ
    -0.10
    æį£
    -0.10
    çħ²
    -0.09
     лег
    -0.09
    нÑĮ
    -0.09
    èĤ¡
    -0.09
    çŃĶåį·
    -0.09
    åĨį度
    -0.08
     odp
    -0.08
     Bose
    -0.08
    POSITIVE LOGITS
    ç©¿æ¢Ń
    0.10
    ssl
    0.09
     HTTPS
    0.09
    schütz
    0.09
    交éĢļè¿IJè¾ĵ
    0.09
    _Request
    0.08
    HTTPS
    0.08
    oref
    0.08
     Erot
    0.08
    æĽ´æĸ°
    0.08
    Activations Density 0.127%

    No Known Activations