© 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. 15889
    Prev
    Next
    INDEX
    Explanations

    by or published by

    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
    è¿ĺ没
    -0.20
    彧
    -0.20
    äºĽ
    -0.19
    马ä¸Ĭ
    -0.19
     barely
    -0.19
    çļĦæł·åŃIJ
    -0.19
    éri
    -0.18
    éĤ£æł·çļĦ
    -0.18
    å°±è¿Ļæł·
    -0.18
    æŶè£ħ
    -0.18
    POSITIVE LOGITS
    ä¼ģä¸ļåľ¨
    0.23
    quartered
    0.22
    ä¼ģä¸ļåıijå±ķ
    0.20
    两家
    0.20
    æ¿ij
    0.19
    为åĩĨ
    0.19
     headquartered
    0.18
     Pierce
    0.18
    tesy
    0.18
    æľįåĬ¡è´¨éĩı
    0.18
    Activations Density 0.002%

    No Known Activations