© 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. 17002
    Prev
    Next
    INDEX
    Explanations

    leadership roles and 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
    Not in Any Lists

    No Comments

    Negative Logits
    åİļåİļ
    -0.19
    èħ¥
    -0.18
    éħ±
    -0.18
     expend
    -0.18
    åıĮæīĭ
    -0.18
     relation
    -0.18
    ä½İ头
    -0.17
    èĦIJ
    -0.17
    CAM
    -0.17
    è¸Ł
    -0.17
    POSITIVE LOGITS
    å«Į
    0.20
    å²Ļ
    0.19
    é¾Ļ头
    0.18
    æĿ¥è®¿
    0.17
    æħ¢æħ¢åľ°
    0.17
    ÑĥеÑĤ
    0.17
    idot
    0.17
    éĶĩ
    0.17
    å³Ļ
    0.17
    é«¡
    0.17
    Activations Density 0.126%

    No Known Activations