© 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. 34148
    Prev
    Next
    INDEX
    Explanations

    countries and continents

    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
    æ³ī
    -0.09
    ä¿ĿåĪ©
    -0.09
    è¿ĽåŁİ
    -0.09
    åįģä¸īå±Ĭ
    -0.09
    ä¸įçŁ¥
    -0.08
    ialect
    -0.08
    çħ¨
    -0.08
    äºķ
    -0.08
    æľĶ
    -0.08
    ç¯Ĩ
    -0.08
    POSITIVE LOGITS
    è£ĺ
    0.09
    对ä¸ŃåĽ½
    0.09
     bang
    0.08
    西æĸ¹
    0.08
     Bang
    0.08
    çĥ¦æģ¼
    0.08
    _wc
    0.08
    mods
    0.08
    è£Ļ
    0.08
    åºĦåĽŃ
    0.08
    Activations Density 0.284%

    No Known Activations