© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11155
    Prev
    Next
    INDEX
    Explanations

    weekdays and days

    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
    KHR
    -0.20
    çī¹åĪ«å£°æĺİ
    -0.20
    .selector
    -0.17
    åħ¨å®¶
    -0.17
    åľ¨çĶŁæ´»ä¸Ń
    -0.17
    è¦ģåģļ好
    -0.16
    çļİ
    -0.16
    éģĵåħ·
    -0.16
    å¤ļå¹´çļĦ
    -0.16
     Gos
    -0.16
    POSITIVE LOGITS
     pragma
    0.19
    .oper
    0.19
    Spr
    0.18
    ç½ķè§ģ
    0.18
    æĿ¡ä»¶ä¸ĭ
    0.18
    æĹ¥åľ¨
    0.17
    orning
    0.17
    .Expr
    0.17
     tầm
    0.17
    æĹ¥æĻļéĹ´
    0.17
    Activations Density 0.004%

    No Known Activations