© 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. 1808
    Prev
    Next
    INDEX
    Explanations

    I, you, actions

    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
     probably
    -0.34
    probably
    -0.27
     certainly
    -0.26
    ;break
    -0.25
     Probably
    -0.25
     often
    -0.23
    纪å§ĶçĽij
    -0.22
    âĢ½
    -0.22
     quite
    -0.22
    _almost
    -0.21
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.46
     ever
    0.34
    ä¸įæħİ
    0.31
     slightest
    0.31
    ever
    0.29
     truly
    0.28
    è¿Ļæł·çļĦè¯Ŀ
    0.28
    æŁIJä¸Ģ
    0.28
    羣çļĦ
    0.27
    ä¸į幸
    0.27
    Activations Density 2.555%

    No Known Activations