© 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. 17047
    Prev
    Next
    INDEX
    Explanations

    isbn or specific Chinese characters

    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
    EventData
    -0.20
    modele
    -0.19
    æĴŃåĩº
    -0.19
    åĨľåİĨ
    -0.19
    èĢĥè¯Ħ
    -0.19
    çŀĴ
    -0.18
     deflect
    -0.18
    罩
    -0.18
    DEFINE
    -0.18
    çĶ¨æ°´
    -0.18
    POSITIVE LOGITS
    åĽ¾ä¹¦é¦Ĩ
    0.29
    åĽ¾ä¹¦
    0.27
    è´¨éĩıéĹ®é¢ĺ
    0.24
    isbn
    0.24
    书
    0.23
    é¦Ĩ
    0.23
    äºĮæīĭ
    0.23
    çĶµåŃIJ产åĵģ
    0.23
    ISBN
    0.22
    履约
    0.22
    Activations Density 0.007%

    No Known Activations