© 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. 11948
    Prev
    Next
    INDEX
    Explanations

    legal statute

    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
    epy
    -0.19
    adius
    -0.19
    æİ¡
    -0.18
    æİ¡åıĸ
    -0.18
    ë§ŀ
    -0.18
    æµĨ
    -0.18
    grave
    -0.18
    彩èĻ¹
    -0.18
     keyValue
    -0.17
    hoc
    -0.17
    POSITIVE LOGITS
     legally
    0.34
    æ³ķå®ļ
    0.32
    æ³ķå¾ĭè§Ħå®ļ
    0.31
    æ³ķè§Ħ
    0.30
    ç«ĭæ³ķ
    0.30
    æĮīè§Ħå®ļ
    0.30
    å¤ĩæ¡Ī
    0.29
     statute
    0.29
     statutory
    0.29
    å®ĺæĸ¹
    0.28
    Activations Density 0.902%

    No Known Activations