© 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. 27444
    Prev
    Next
    INDEX
    Explanations

    defibrillator / cardioverter

    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¸įåIJĥ
    -0.10
    çłĴ
    -0.10
    æIJŀ好
    -0.09
    åIJĥè¿ĩ
    -0.09
    æħ§
    -0.09
    Fore
    -0.09
    SEM
    -0.09
    æ¯ģ
    -0.09
    庵
    -0.09
    æ§Ł
    -0.09
    POSITIVE LOGITS
    åĪĽæĸ°é©±åĬ¨
    0.10
    æĭ³å¤´
    0.09
    æĿĤ
    0.09
    ç´Ĭä¹±
    0.09
    ç»Ĵ
    0.09
    æIJºå¸¦
    0.09
    失èIJ½
    0.08
    èĬĻèĵī
    0.08
    èį·èĬ±
    0.08
    .ecore
    0.08
    Activations Density 0.141%

    No Known Activations