© 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. 47398
    Prev
    Next
    INDEX
    Explanations

    rely upon/on

    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
    ity
    -0.10
    ially
    -0.09
    ateur
    -0.09
    å¸Ļ
    -0.09
    eso
    -0.09
    éļħ
    -0.09
    å¤±æľĽ
    -0.08
    çīĸ
    -0.08
    terr
    -0.08
    erial
    -0.08
    POSITIVE LOGITS
    ambda
    0.12
    ðŁı»
    0.11
    æĭ¢
    0.11
    å¾Ĺä½ı
    0.11
    aign
    0.10
    à¸Ńาศ
    0.10
    lessly
    0.10
    uper
    0.10
    ndon
    0.09
     ÑģобиÑĢа
    0.09
    Activations Density 0.006%

    No Known Activations