© 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. 2285
    Prev
    Next
    INDEX
    Explanations

    legal acts and documents

    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
     Osman
    -0.09
    æ·¦
    -0.09
    spd
    -0.08
    æķĽ
    -0.07
    åĬŁ
    -0.07
    .getM
    -0.07
    éĻĩ
    -0.07
     Chamber
    -0.07
    Outlet
    -0.07
    ILA
    -0.07
    POSITIVE LOGITS
    åįĸç»Ļ
    0.11
    åıijçĶŁåľ¨
    0.10
    æĹ¥çħ§
    0.10
    ä¸įåħ¬å¹³
    0.10
    æļij
    0.09
    ä¼ĺæĥł
    0.09
    Unchecked
    0.09
    幡
    0.09
    çIJIJ
    0.09
    è§Ħç«ł
    0.09
    Activations Density 0.071%

    No Known Activations