© 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. 26047
    Prev
    Next
    INDEX
    Explanations

    sky related terms

    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
    ucc
    -0.10
    oref
    -0.09
     xuyên
    -0.09
    sen
    -0.09
    uth
    -0.09
    cep
    -0.09
    ½æķ°
    -0.09
    esa
    -0.09
    sing
    -0.09
    svp
    -0.08
    POSITIVE LOGITS
    0.14
    lights
    0.12
    walker
    0.11
    -blue
    0.11
    lining
    0.11
    à¸ĩาà¸Ļ
    0.10
    watch
    0.10
    ridge
    0.10
    waves
    0.10
    shots
    0.10
    Activations Density 0.013%

    No Known Activations