© 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. 13529
    Prev
    Next
    INDEX
    Explanations

    Names and foreign words

    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
    çļĦ表çİ°
    -0.20
    unnel
    -0.20
    寡
    -0.19
    ä¸Ģå¤ľ
    -0.19
    çļĦæĦıæĢĿ
    -0.18
     plural
    -0.18
     ven
    -0.18
    ведениÑı
    -0.17
     coc
    -0.17
     apparent
    -0.17
    POSITIVE LOGITS
    åĨľåī¯äº§åĵģ
    0.20
    éĿĴå±±
    0.18
    æĶ¹éĿ©å§Ķ
    0.18
    èĭij
    0.18
    LocalizedString
    0.17
    æ¡ĤèĬ±
    0.17
    åıijè¨Ģ人
    0.17
    说åĪ°è¿ĻéĩĮ
    0.17
     Arbitrary
    0.17
    水稻
    0.16
    Activations Density 0.092%

    No Known Activations