© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1069
    Prev
    Next
    INDEX
    Explanations

    code/url parts

    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
    arriv
    -0.24
    ä¸ī大éĺ¶æ®µ
    -0.24
    ç½ijåıĭ们
    -0.24
     burge
    -0.24
     applyMiddleware
    -0.22
    å°ıä¼Ļ伴们
    -0.22
    åľ¨çº¿åĴ¨è¯¢
    -0.22
    综èīºèĬĤ缮
    -0.21
    åķ«
    -0.21
    ])==
    -0.21
    POSITIVE LOGITS
    -Cs
    0.28
    ,");↵
    0.24
    -urlencoded
    0.22
    /MPL
    0.22
    :animated
    0.21
    :NO
    0.21
    /↵↵↵↵
    0.21
     volunte
    0.21
    edelta
    0.20
    âļĹ
    0.20
    Activations Density 5.724%

    No Known Activations