© 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. 12348
    Prev
    Next
    INDEX
    Explanations

    nuances and shades

    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
    Ñīен
    -0.20
    éªĭ
    -0.17
    achu
    -0.17
    åIJįçīĩ
    -0.17
    åIJijä¸ĭ
    -0.17
    约æĿŁ
    -0.17
    ä¹Łæĺ¯ä¸Ģç§į
    -0.17
    é¼ĵåĬ±
    -0.17
    豫
    -0.16
    ç£Ĭ
    -0.16
    POSITIVE LOGITS
     nuances
    0.29
     shades
    0.24
    åıĺåĮĸ
    0.22
    ynet
    0.21
    ä¸įæ¸ħ
    0.21
    å¾®å¦Ļ
    0.21
    ç»Ĩå¾®
    0.21
     nuanced
    0.20
    ls
    0.19
    ç»Ĩèħ»
    0.19
    Activations Density 0.017%

    No Known Activations