© 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. 27584
    Prev
    Next
    INDEX
    Explanations

    phrases after punctuation

    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
    ë²Į
    -0.11
    ayo
    -0.10
    acement
    -0.10
    ucer
    -0.10
    برÙĬ
    -0.10
    asher
    -0.09
    è°ħ
    -0.09
    _UTF
    -0.09
    è´Łæĭħ
    -0.09
     Bare
    -0.09
    POSITIVE LOGITS
    lei
    0.08
    ä¼ļ议精ç¥ŀ
    0.08
    çļĦ帮åĬ©ä¸ĭ
    0.07
    éĺĹ
    0.07
    éĢĶ
    0.07
     own
    0.07
     sno
    0.07
     Sr
    0.07
    人æ°ijæľįåĬ¡
    0.07
    apro
    0.07
    Activations Density 0.266%

    No Known Activations