© 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. 56328
    Prev
    Next
    INDEX
    Explanations

    cities and their descriptions

    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¸Ģç»Ħ
    -0.11
    å¿ĥ仪çļĦ
    -0.11
    æİ¥åıĹéĩĩ访
    -0.10
    æĿĢæīĭ
    -0.10
    تÙĩ
    -0.09
    æĦį
    -0.09
    åĮĹ京大åѦ
    -0.09
    èĥ½åĬĽåĴĮ
    -0.09
    æĮģå¹³
    -0.09
     завод
    -0.09
    POSITIVE LOGITS
    ç±į
    0.09
    è¿Ļ座
    0.08
     culture
    0.08
    culture
    0.08
    è¿Ļä¸ªåľ°æĸ¹
    0.08
    æĸĩåĮĸçļĦ
    0.08
    Xi
    0.08
    é¦Ī
    0.08
    razier
    0.08
     moder
    0.08
    Activations Density 0.104%

    No Known Activations