© 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. 39738
    Prev
    Next
    INDEX
    Explanations

    can do/buy/awarded/at/have

    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
    æĽ´å¥½çļĦ
    -0.10
    çIJĨæĥ³çļĦ
    -0.10
     Adoles
    -0.09
    æĽ´å¤ļ精彩
    -0.09
    æ¥Ķ
    -0.09
    illion
    -0.09
     Gale
    -0.09
    usi
    -0.08
    villa
    -0.08
    第ä¸Ģ个
    -0.08
    POSITIVE LOGITS
    èİ«è¿ĩäºİ
    0.11
    8
    0.11
    ç¼Ł
    0.11
    è¿Ļ件äºĭæĥħ
    0.11
    6
    0.10
    7
    0.10
    4
    0.10
    ä¸Ģç¬Ķ
    0.10
    0
    0.10
    3
    0.10
    Activations Density 0.034%

    No Known Activations