© 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. 64126
    Prev
    Next
    INDEX
    Explanations

    following intuition or instinct

    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
    æĹłæĦı
    -0.12
    çĨĦ
    -0.10
    umer
    -0.09
    æ¿¡
    -0.08
    ç¢Į
    -0.08
    åĩ¼
    -0.08
    é¬ĵ
    -0.08
    atoi
    -0.08
     urlencode
    -0.08
    论述
    -0.08
    POSITIVE LOGITS
    æľ¬èĥ½
    0.17
     instincts
    0.17
     intuition
    0.14
     gut
    0.12
     instinct
    0.12
    inst
    0.11
    åĩŃ
    0.11
    æĦŁåıĹ
    0.10
    äºĨèĩªå·±çļĦ
    0.10
    èĩªå·±çļĦ
    0.10
    Activations Density 0.032%

    No Known Activations