© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29507
    Prev
    Next
    INDEX
    Explanations

    a proportion of

    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
    Negative Logits
    Recognizer
    -0.09
    ä¸ĢçĤ¹åĦ¿
    -0.08
    åĽĽé¡¹
    -0.08
     antiqu
    -0.08
    agers
    -0.08
    åħ¨å¥Ĺ
    -0.08
     complex
    -0.08
    缮
    -0.08
    maj
    -0.07
    ç¾ļ
    -0.07
    POSITIVE LOGITS
    ä¸Ģéĥ¨åĪĨ
    0.19
    å°ijæķ°
    0.18
    çļĦä¸Ģéĥ¨åĪĨ
    0.14
    æľīå¤ļå°ij
    0.14
    大éĥ¨åĪĨ人
    0.14
    人群
    0.13
    ä¸Ģ群人
    0.13
    éĥ¨åĪĨ
    0.13
    大å¤ļæķ°äºº
    0.13
    éĥ¨ä»½
    0.13
    Activations Density 0.323%

    No Known Activations