© 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. 28106
    Prev
    Next
    INDEX
    Explanations

    .runner / .runners

    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
     tá»ĩ
    -0.09
    cente
    -0.09
    缮çļĦåľ°
    -0.08
    èĪIJ
    -0.08
    IFF
    -0.08
    æݬ
    -0.08
    太è¿ĩ
    -0.08
    çĤ¸
    -0.08
    umu
    -0.08
     tá»ĵ
    -0.08
    POSITIVE LOGITS
    为æĤ¨æıIJä¾Ľ
    0.11
    .runners
    0.10
    ãĤªãĥªãĤ¸ãĥĬãĥ«
    0.09
    çĶ¨å·¥
    0.09
    为æĤ¨
    0.09
    ä¸ļåĨħ
    0.08
    让æ¶Īè´¹èĢħ
    0.08
    å¸ĤéĿ¢ä¸Ĭ
    0.08
    æı
    0.08
    .runner
    0.08
    Activations Density 0.147%

    No Known Activations