© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 340
    Prev
    Next
    INDEX
    Explanations

    indeed, actually

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    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
    æį®è¯´
    -0.32
     reportedly
    -0.31
    æĪijè§īå¾Ĺ
    -0.28
    åı¯æĥ³èĢĮçŁ¥
    -0.28
    æį®
    -0.28
    :CGRect
    -0.27
    æĪijçŁ¥éģĵ
    -0.27
    æĪijçĽ¸ä¿¡
    -0.27
    æį®ç»Łè®¡
    -0.26
     misd
    -0.26
    POSITIVE LOGITS
     indeed
    0.49
     ÙĪØ£ÙĨ
    0.36
     Indeed
    0.36
    inde
    0.33
     somehow
    0.33
    Indeed
    0.29
     actually
    0.29
    ç¡®å®ŀ
    0.29
    actually
    0.27
    æľīå¤ļä¹Ī
    0.27
    Activations Density 4.069%

    No Known Activations