© 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. 39062
    Prev
    Next
    INDEX
    Explanations

    want to

    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
    å¥Ī
    -0.11
    è¦ģ好好
    -0.10
     thủ
    -0.09
    likely
    -0.09
    æĬ¥èĢĥ
    -0.09
    lopedia
    -0.09
    ä¸Ĭæ¦ľ
    -0.09
    ì¤Ħ
    -0.09
    .newLine
    -0.09
    اÙģÙĬØ©
    -0.09
    POSITIVE LOGITS
    æ¯Ķå¦Ĥ
    0.11
    ä¸ĩä¸Ģ
    0.09
    éģĩä¸Ĭ
    0.09
    åij¢
    0.09
    çªģçĦ¶
    0.09
    æł¹æľ¬å°±ä¸į
    0.09
     suddenly
    0.09
    ä¸įå°ıå¿ĥ
    0.09
    åĸĦæĦı
    0.09
    rica
    0.09
    Activations Density 0.150%

    No Known Activations