© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 27217
    Prev
    Next
    INDEX
    Explanations

    university names and states

    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
    æ»Ķ
    -0.09
    æĿł
    -0.09
    èĪĮ头
    -0.09
    BILL
    -0.09
    ç»Ŀ大éĥ¨åĪĨ
    -0.09
     Mattis
    -0.09
    ä»ħ次äºİ
    -0.08
    hands
    -0.08
    说åĩºæĿ¥
    -0.08
    æ½ĩ
    -0.08
    POSITIVE LOGITS
    vice
    0.11
    èĥĮ
    0.09
    ople
    0.09
    èĥĮä¸Ĭ
    0.08
    èĭıå·ŀ
    0.08
    罩
    0.08
    оÑħÑĢан
    0.08
     Nhi
    0.08
    çĨŁ
    0.08
     Sic
    0.08
    Activations Density 0.013%

    No Known Activations