© 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. 57818
    Prev
    Next
    INDEX
    Explanations

    AJAX requests

    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
    _heading
    -0.09
    ç¬Ķè®°æľ¬
    -0.09
    è§Ħ模
    -0.09
    æľīæľºä¼ļ
    -0.09
    ä»Ģä¹Īäºĭ
    -0.08
    çļĦå®ŀåĬĽ
    -0.08
    _TI
    -0.08
    éļıæĦı
    -0.08
    路人
    -0.08
    代çIJĨåķĨ
    -0.08
    POSITIVE LOGITS
    _ajax
    0.11
     Ajax
    0.11
    Ajax
    0.11
    /ajax
    0.10
     Hou
    0.10
    .ajax
    0.10
    LIK
    0.10
    ä¸Ģå¿ĥ
    0.09
     JsonRequest
    0.09
    ajax
    0.09
    Activations Density 0.498%

    No Known Activations