© 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. 39570
    Prev
    Next
    INDEX
    Explanations

    privacy and policy statements

    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»Ģä¹Īä¸ľè¥¿
    -0.11
    åĮ¹
    -0.10
    åĭī强
    -0.09
    æ°ª
    -0.09
    æŃ£å¥½
    -0.09
    ä¸ķ
    -0.09
    åįĬ个
    -0.09
    ä¸ĢèĤ¡
    -0.09
    天é¹ħ
    -0.08
    æģ°å¥½
    -0.08
    POSITIVE LOGITS
     Barnett
    0.10
    æĬĬè¿Ļ个
    0.09
    åıĮéĩį
    0.08
    èĤĥ
    0.08
    FileSync
    0.08
     cuff
    0.08
    æŁĦ
    0.08
    éĿĴéĵľ
    0.08
     Latvia
    0.08
    uli
    0.07
    Activations Density 0.012%

    No Known Activations