© 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. 16858
    Prev
    Next
    INDEX
    Explanations

    copy and paste operations

    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
     اÙĦØ°
    -0.10
    åĺ´éĩĮ
    -0.10
    orida
    -0.10
    اث
    -0.10
    çŃīåĢĻ
    -0.09
    _void
    -0.09
    idel
    -0.09
    åŁİå¸Ĥåıijå±ķ
    -0.09
    ä¸į符
    -0.09
    sWith
    -0.09
    POSITIVE LOGITS
    æѤ
    0.08
    essen
    0.07
    /comment
    0.07
    íĦ°
    0.07
    ä¸įèĩ³äºİ
    0.07
     aÅŁaģıdaki
    0.07
    åĢŁåı£
    0.07
     Cunningham
    0.07
    å©´
    0.07
    g
    0.07
    Activations Density 0.038%

    No Known Activations