© 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. 47618
    Prev
    Next
    INDEX
    Explanations

    carry or carrying

    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
    ively
    -0.09
    å°¼äºļ
    -0.09
    entic
    -0.09
    ened
    -0.08
    sky
    -0.08
    FIXME
    -0.08
    æķĪ
    -0.08
     Elephant
    -0.08
    èĨĽ
    -0.08
    æīĭä¸ĭ
    -0.08
    POSITIVE LOGITS
    æĭ¯
    0.11
    é½IJåħ¨
    0.09
    帰
    0.09
    ngo
    0.09
    æŶæĬ¥
    0.09
    หาย
    0.09
    rello
    0.08
    abouts
    0.08
    ndon
    0.08
    AppBundle
    0.08
    Activations Density 0.015%

    No Known Activations