© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10564
    Prev
    Next
    INDEX
    Explanations

    company names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     kiá»ĩn
    -0.19
    ulado
    -0.19
    èĶº
    -0.18
    ÑĥÑĪ
    -0.18
    ë¹Ļ
    -0.18
    geführt
    -0.18
    ides
    -0.18
    ills
    -0.17
    tries
    -0.17
    èĵ
    -0.17
    POSITIVE LOGITS
     Visitor
    0.19
    âĩ¢
    0.18
    PURE
    0.18
     дал
    0.18
    èįĴ
    0.17
    åĩĨ
    0.17
    Anywhere
    0.17
    maf
    0.16
    ReturnValue
    0.16
    âĻ£
    0.16
    Activations Density 0.002%

    No Known Activations