© 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. 59248
    Prev
    Next
    INDEX
    Explanations

    lifestyle

    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
    ç®Ķ
    -0.10
    åĿĽ
    -0.10
     зÑĢениÑı
    -0.09
     Hai
    -0.09
    éĻĮçĶŁ
    -0.09
    ä¸įåĪ°
    -0.09
    eted
    -0.09
    oted
    -0.08
    èĮĶ
    -0.08
    ç°ĭ
    -0.08
    POSITIVE LOGITS
    вл
    0.11
    ayed
    0.10
    ellaneous
    0.09
     lifestyles
    0.09
    indent
    0.09
     quo
    0.09
    zech
    0.09
    åĴĮæĬĢæľ¯
    0.08
    çĶ¨åĵģ
    0.08
    į
    0.08
    Activations Density 0.007%

    No Known Activations