© 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. 10625
    Prev
    Next
    INDEX
    Explanations

    science fiction authors and books

    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
    ç¬ijèĦ¸
    -0.22
    orus
    -0.21
    OMPI
    -0.21
    enville
    -0.21
    ypad
    -0.21
    æĽĿåħī
    -0.20
    оÑĢа
    -0.20
    _dbg
    -0.20
    -picker
    -0.20
    /libs
    -0.20
    POSITIVE LOGITS
    ç§ijå¹»
    0.33
    åĨĻä½ľ
    0.24
    å°ı说
    0.23
    æ§İ
    0.22
     worlds
    0.22
    gal
    0.21
    ä½ľåĵģ
    0.21
    壬
    0.21
     Worlds
    0.20
    ä¸ĸçķĮè§Ĥ
    0.20
    Activations Density 0.060%

    No Known Activations