© 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. 18491
    Prev
    Next
    INDEX
    Explanations

    Code generated by the command above; see README

    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
    ellig
    -0.09
     ÑģпÑĢав
    -0.09
    大å¹ħæıIJåįĩ
    -0.08
    åIJ¸å¼ķåĬĽ
    -0.08
    足足
    -0.07
    OH
    -0.07
     Able
    -0.07
     soft
    -0.07
    å²±
    -0.07
    ALER
    -0.07
    POSITIVE LOGITS
    è¦ĨçĽĸéĿ¢
    0.10
    对该
    0.10
    ä¸į代表
    0.10
    æĬĬå®ĥ
    0.10
    为äºĨæĽ´å¥½
    0.10
    ä¹°åįķ
    0.10
    æľªç»ıæİĪæĿĥ
    0.09
    çīĪæĿĥå½ĴåİŁ
    0.09
    ä¹Łåı¯
    0.09
     Disclaimer
    0.09
    Activations Density 0.030%

    No Known Activations