© 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. 10632
    Prev
    Next
    INDEX
    Explanations

    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
    Not in Any Lists

    No Comments

    Negative Logits
    第ä¸ĢæĿ¡
    -0.21
    .getCurrentUser
    -0.18
     Friendship
    -0.18
    æ´ĭæ´ĭ
    -0.17
    æīįåıijçİ°
    -0.17
    elize
    -0.17
    ä¸ŃåѦ
    -0.17
    交åıĭ
    -0.17
    hlen
    -0.17
    ToF
    -0.17
    POSITIVE LOGITS
    ç»ĦæĪIJçļĦ
    0.28
    ç°ĩ
    0.23
    ì§ľ
    0.21
    ç»ĦæĪIJ
    0.20
    纸ä¸Ĭ
    0.19
    acters
    0.19
    ä¹ĭéĹ´çļĦ
    0.19
    ularity
    0.18
    æŀĦæĪIJ
    0.18
    æŁĶ
    0.18
    Activations Density 0.206%

    No Known Activations