© 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. 6186
    Prev
    Next
    INDEX
    Explanations

    personalized message or imprint

    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
     consort
    -0.09
    åĿIJä¸ĭ
    -0.08
     sweeps
    -0.08
    zik
    -0.08
    æ±ŁåĮĹ
    -0.08
    åĿIJåľ¨
    -0.08
     اÙĦÙħص
    -0.08
    åıijçİ°éĹ®é¢ĺ
    -0.08
     Aur
    -0.08
    姿åĬ¿
    -0.08
    POSITIVE LOGITS
    ä¸įä¿¡
    0.12
    éķĮ
    0.12
    个æĢ§åĮĸ
    0.10
    éĵŃè®°
    0.10
    涯
    0.10
    åĪ»
    0.10
    亲åıĭ
    0.10
    å®ļåĪ¶
    0.09
    ä¸Ģåı¥
    0.09
    è¾Ī
    0.09
    Activations Density 0.035%

    No Known Activations