© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12655
    Prev
    Next
    INDEX
    Explanations

    regular school begins

    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
     fame
    -0.26
     I
    -0.22
    ,
    -0.21
    æĪIJåIJį
    -0.21
     barely
    -0.21
    æĺĶ
    -0.20
     railways
    -0.20
     Fernando
    -0.20
     sometimes
    -0.20
    let
    -0.20
    POSITIVE LOGITS
    ä¾ĭå¤ĸ
    0.32
    继ç»Ńä¿ĿæĮģ
    0.32
    æģ¢å¤įæŃ£å¸¸
    0.30
    æŃ£å¸¸çļĦ
    0.28
    çݩ家æľĭåıĭ
    0.26
     salopes
    0.26
    çī¹æ®ĬæĥħåĨµ
    0.26
    à¦Ī
    0.26
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    0.26
    çļĦéĢļçŁ¥
    0.26
    Activations Density 0.051%

    No Known Activations