© 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. 17189
    Prev
    Next
    INDEX
    Explanations

    version information or legal mentions

    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
     lessons
    -0.21
    amat
    -0.20
    bor
    -0.20
    å¦Ļ
    -0.19
    åĸĿ
    -0.19
    æĺ¥å¤©
    -0.19
    好æ¶Īæģ¯
    -0.19
    é¦ĸ缸
    -0.19
    ind
    -0.18
    èĢ¸
    -0.18
    POSITIVE LOGITS
    icie
    0.23
     addCriterion
    0.20
    actionDate
    0.20
    ész
    0.19
     NSData
    0.19
    æ´İ
    0.19
     Kash
    0.19
    rés
    0.19
    åıijæĮ¥ä½ľçĶ¨
    0.18
    ÑģÑĤа
    0.18
    Activations Density 0.036%

    No Known Activations