© 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. 579
    Prev
    Next
    INDEX
    Explanations

    earn and what is earned

    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
    ENTS
    -0.11
    æŃĨ
    -0.10
    kol
    -0.10
    ively
    -0.10
    pent
    -0.09
    ONTAL
    -0.09
    _endian
    -0.09
    cao
    -0.09
     Valerie
    -0.09
    èĨ³é£Ł
    -0.09
    POSITIVE LOGITS
    shaw
    0.13
    /disable
    0.10
    velope
    0.10
    arie
    0.09
    igans
    0.09
    fully
    0.09
    ough
    0.09
    æĹĥ
    0.09
    é©·
    0.09
    æŶæĬ¥
    0.09
    Activations Density 0.012%

    No Known Activations