© 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. 40335
    Prev
    Next
    INDEX
    Explanations

    m words

    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
    جÙĪ
    -0.09
    ective
    -0.09
    REW
    -0.09
    èĩ³äºİ
    -0.09
    èĨľ
    -0.09
    ekt
    -0.08
    WAYS
    -0.08
    Ñģкоп
    -0.08
    æľīåIJįçļĦ
    -0.08
    ULL
    -0.08
    POSITIVE LOGITS
    æĺ§
    0.09
    伤
    0.09
    appable
    0.09
    azine
    0.09
    akin
    0.09
    æľīæīĢ
    0.08
    饰
    0.08
    çł»
    0.08
     жизни
    0.08
    ugged
    0.08
    Activations Density 0.044%

    No Known Activations