© 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. 24321
    Prev
    Next
    INDEX
    Explanations

    support for

    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
    éŃĤ
    -0.10
    åŃIJéĩĮ
    -0.08
    ä¸Ģ声
    -0.08
     themselves
    -0.08
    eger
    -0.08
    ette
    -0.08
    ãĥ³ãĤ°
    -0.08
    åľ¨åĨħçļĦ
    -0.08
    审çIJĨ
    -0.08
    åĩĨåħ¥
    -0.08
    POSITIVE LOGITS
     اÙĦÙħص
    0.11
    åĴĮæĶ¯æĮģ
    0.10
    /support
    0.10
    人士
    0.09
    rooms
    0.09
    fulness
    0.09
    ÑĩÑĮ
    0.09
    geber
    0.09
     воÑģ
    0.09
    amu
    0.09
    Activations Density 0.029%

    No Known Activations