© 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. 59187
    Prev
    Next
    INDEX
    Explanations

    state of being asleep

    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
    å·¥ä½ľå²Ĺä½į
    -0.11
    姥姥
    -0.10
    æĸ°é¢ĸ
    -0.09
    ãģĹãģ¦ãĤĤ
    -0.09
     AFF
    -0.08
    èį©
    -0.08
    èįı
    -0.08
    forth
    -0.08
    ont
    -0.08
    èĪĮå°ĸ
    -0.08
    POSITIVE LOGITS
    ä¸ĵ享
    0.10
    ãģĦãĤĦ
    0.10
    çĿ¡
    0.09
    ãģĵãĤĵ
    0.09
    ittings
    0.08
    éĻµ
    0.08
    è¾ĩ
    0.08
    zew
    0.08
    ä¸į太好
    0.08
    çľł
    0.08
    Activations Density 0.148%

    No Known Activations