© 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. 50190
    Prev
    Next
    INDEX
    Explanations

    via the internet

    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
    家åĸ»æĪ·æĻĵ
    -0.08
     olacaktır
    -0.08
    è¿ĺå°Ĩ
    -0.08
    éĢĤ
    -0.08
    æĿľç»Ŀ
    -0.08
    æĽ¾
    -0.08
    unte
    -0.08
    lobber
    -0.08
    été
    -0.07
    åģļ强
    -0.07
    POSITIVE LOGITS
    æŁIJç§į
    0.15
    çļĦä¸Ģç§į
    0.13
    è¦ģä¹Ī
    0.13
     either
    0.13
    either
    0.12
    æŁIJ个
    0.12
    åijĹ
    0.11
    æĪĸå¤ļæĪĸå°ij
    0.11
    æŁIJä¸Ģ
    0.11
    éĢļ常æĺ¯
    0.11
    Activations Density 0.908%

    No Known Activations