© 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. 54238
    Prev
    Next
    INDEX
    Explanations

    picking me

    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
    çŁ¥éģĵèĩªå·±
    -0.08
    幡
    -0.08
    zc
    -0.08
    KF
    -0.08
    æĬĹ
    -0.08
    ãĥ¡
    -0.08
    æĤł
    -0.08
     ski
    -0.08
    è§IJ
    -0.08
    åĽŀåij³
    -0.07
    POSITIVE LOGITS
    ä¼łæİĪ
    0.15
    å¸®ä½ł
    0.15
    让大家
    0.15
    å¸¦ä½ł
    0.14
    æıIJä¾Ľ
    0.14
    é¼ĵåĬ±
    0.14
    å¼ķ导
    0.13
    让æĤ¨
    0.13
    è®©ä½ł
    0.13
    带ç»Ļ
    0.13
    Activations Density 0.376%

    No Known Activations