© 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. 493
    Prev
    Next
    INDEX
    Explanations

    code and file names

    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
    ï¹Ĺ
    -0.33
    utow
    -0.29
    ç»ĻåĬĽ
    -0.25
    æīĢæľīæĥħèĬĤ
    -0.25
    /vendors
    -0.25
    ðŁļ©
    -0.25
    å°±å¤Ł
    -0.25
    Ulus
    -0.25
    家åĸ»
    -0.24
    ä¹Łä¸įéĶĻ
    -0.24
    POSITIVE LOGITS
    ç½ijé¦ĸ页
    0.28
     Reached
    0.28
    éĥ¨åī¯
    0.27
    ä¼ļä¼ļéķ¿
    0.27
    íĶĦë¡ľê·¸
    0.26
     hurd
    0.25
    GLenum
    0.25
     POSSIBILITY
    0.25
    åij¸
    0.24
     :↵↵↵↵
    0.24
    Activations Density 8.242%

    No Known Activations