© 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. 33326
    Prev
    Next
    INDEX
    Explanations

    ways to do something

    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
    ени
    -0.08
    ksen
    -0.08
    裾
    -0.08
    éģ¨
    -0.08
    arend
    -0.08
     Beste
    -0.08
    æ¥Ķ
    -0.07
    åŁºæķ°
    -0.07
    arters
    -0.07
    ترÙĨت
    -0.07
    POSITIVE LOGITS
     ways
    0.11
    çļĦ帮åĬ©
    0.11
    çİ©æ³ķ
    0.11
     Ways
    0.10
    ide
    0.10
    åĤ§
    0.09
    æĸ¹éĿ¢çļĦ
    0.09
    éļIJéļIJ
    0.09
    anel
    0.09
    æīĵå¾Ĺ
    0.09
    Activations Density 0.037%

    No Known Activations