© 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. 6412
    Prev
    Next
    INDEX
    Explanations

    demands and actions

    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
    åIJĪä½ľåħ³ç³»
    -0.10
    æĹ¶ä»£çļĦ
    -0.09
    bett
    -0.09
    ä½ľä¸ºä¸ĢåIJį
    -0.09
    åģļ人
    -0.08
    çķĻç»Ļ
    -0.08
    çªij
    -0.08
    便
    -0.08
    代价
    -0.08
    éºĿ
    -0.08
    POSITIVE LOGITS
    åĴĮ社ä¼ļ
    0.12
    æĮĸ
    0.09
    åĴĮåľ°åĮº
    0.09
    åĴĮ个人
    0.08
     tame
    0.08
    è¡·
    0.08
    æ½¼
    0.08
    è¿Ļæĸ¹éĿ¢
    0.08
    ÂŃs
    0.08
    ä¸ĢåĪĩéĥ½æĺ¯
    0.08
    Activations Density 0.266%

    No Known Activations