© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7075
    Prev
    Next
    INDEX
    Explanations

    dental implants

    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
    å·¡èĪª
    -0.09
     недо
    -0.09
    piel
    -0.09
    asion
    -0.09
    ç²ĴåŃIJ
    -0.09
    çł£
    -0.08
    æ³ķåºŃ
    -0.08
    è·¯éĿ¢
    -0.08
    åľºåľ°
    -0.08
    browse
    -0.08
    POSITIVE LOGITS
     Inn
    0.09
    缼ä¸ĸ
    0.08
     Certified
    0.08
    é¾Ļæ¹ĸ
    0.08
    èķŀ
    0.08
    åĽĽä½į
    0.08
    è¹
    0.08
     Plot
    0.08
    çļĦæĸ°
    0.08
    Plot
    0.08
    Activations Density 0.222%

    No Known Activations