© 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. 4507
    Prev
    Next
    INDEX
    Explanations

    whether you care

    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
    ä¸įä»ħ
    -0.09
    ä¸İä¸ŃåĽ½
    -0.09
    eria
    -0.08
    à¸Ľà¸£à¸°
    -0.08
    èĩ³å°ij
    -0.08
    ä¸įåĥħ
    -0.08
     enjo
    -0.08
    obia
    -0.08
    ä¸į容
    -0.08
     вÑģей
    -0.08
    POSITIVE LOGITS
    èĢĮæĺ¯
    0.12
    ä¸İåIJ¦
    0.11
     WHETHER
    0.11
    绶
    0.10
    èĥª
    0.10
    æļĤæŶ
    0.10
     æĺ¯åIJ¦
    0.09
    æĺ¯åIJ¦
    0.09
    åIJĥä»Ģä¹Ī
    0.09
     Whether
    0.09
    Activations Density 0.066%

    No Known Activations