© 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. 13534
    Prev
    Next
    INDEX
    Explanations

    plans to

    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
    çªģåıijäºĭ件
    -0.21
    认è¯ĨåĪ°
    -0.20
    ä¸įå¾Ĺä¸į说
    -0.20
    å°¼æĸ¯
    -0.20
    好å¥ĩå¿ĥ
    -0.20
    éļ¾éģĵ
    -0.19
    æľīæŶåĢĻ
    -0.19
    åıijçİ°èĩªå·±
    -0.19
    æĪijåıijçİ°
    -0.19
    人æµģ
    -0.18
    POSITIVE LOGITS
    å·²ä¹ħçļĦ
    0.28
    å·²ä¹ħ
    0.25
    edly
    0.25
    åľ¨æľªæĿ¥
    0.24
    æīĵç®Ĺ
    0.22
     plans
    0.21
    计åĪĴ
    0.21
    aller
    0.20
    æľªæĿ¥çļĦ
    0.19
     future
    0.19
    Activations Density 0.040%

    No Known Activations