© 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. 60737
    Prev
    Next
    INDEX
    Explanations

    census data and statistics

    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
    æĹĹä¸ĭ
    -0.09
    俾
    -0.08
    æĸ°å½¢åĬ¿ä¸ĭ
    -0.08
    è³´
    -0.08
    æľĿçĿĢ
    -0.08
    ä¸ĸçķĮä¸Ĭ
    -0.08
    亿åħĥ以ä¸Ĭ
    -0.08
    coe
    -0.08
     hypoc
    -0.08
    _characters
    -0.08
    POSITIVE LOGITS
    acic
    0.10
    rella
    0.09
     Ø£ÙĦÙģ
    0.08
    äs
    0.08
    ALER
    0.08
    æīĴ
    0.08
    linger
    0.08
    å´ĸ
    0.08
    ç©¿
    0.08
    ANE
    0.08
    Activations Density 0.174%

    No Known Activations