© 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. 17179
    Prev
    Next
    INDEX
    Explanations

    part of

    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
    èĪĢ
    -0.20
    orest
    -0.20
    ç»Ļä½łä»¬
    -0.19
    缨
    -0.19
    ä¼
    -0.19
    acock
    -0.19
    inue
    -0.19
    èĩ¼
    -0.18
    aly
    -0.18
    cer
    -0.18
    POSITIVE LOGITS
    羣å¿ĥ
    0.21
    æİĮæı¡
    0.20
    èĮĥæĸĩ
    0.20
    inde
    0.19
    ç´¢
    0.19
    loi
    0.19
     Griff
    0.18
    为äºĨ让
    0.18
     Blick
    0.18
    _clause
    0.18
    Activations Density 0.011%

    No Known Activations