© 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. 59283
    Prev
    Next
    INDEX
    Explanations

    planning and strategy

    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
    oha
    -0.10
    ç»ĿæľĽ
    -0.10
    èIJĮ
    -0.10
    åľ¨æĦı
    -0.09
    æĸ°é¢ĸ
    -0.09
    èµģ
    -0.09
    ä½ĵä¼ļ
    -0.09
    ombat
    -0.09
    æĸ°åĵģ
    -0.08
    izr
    -0.08
    POSITIVE LOGITS
    è§ĦåĪĴ
    0.16
    æĢ»ä½ĵè§ĦåĪĴ
    0.15
    è¦ıåĬĥ
    0.12
    æľªæĿ¥
    0.12
    è¿ľæĻ¯
    0.11
    åıijå±ķè§ĦåĪĴ
    0.11
    æĮĩ导æĦıè§ģ
    0.10
     planner
    0.10
    æľªä¾Ĩ
    0.10
    éķ¿è¿ľ
    0.10
    Activations Density 0.038%

    No Known Activations