© 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. 58713
    Prev
    Next
    INDEX
    Explanations

    unnamed, unidentified, or unknown entities

    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
     Hercules
    -0.09
    åıĮéĩį
    -0.08
    æ°´åĪĨ
    -0.08
    Fal
    -0.08
     Rad
    -0.08
    ä¸įæķ¢
    -0.08
    åłªç§°
    -0.08
    Rad
    -0.08
    毫ä¸į
    -0.08
     Gör
    -0.08
    POSITIVE LOGITS
    çĶ¨æĪ·æıIJä¾Ľ
    0.10
    å·²ä¹ħçļĦ
    0.10
     unspecified
    0.09
    æļĸ
    0.09
    alah
    0.09
    ãĥĥãĤ·ãĥ¥
    0.09
    çĩİ
    0.09
    è§ĦåĪĴ建设
    0.09
    稿
    0.09
    çĶļèĩ³è¿ŀ
    0.09
    Activations Density 0.055%

    No Known Activations