© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-CHAT-65K
    7. 46306
    Prev
    Next
    INDEX
    Explanations

    drive

    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/lmsys/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 192 tokens each
    Dataset (Dashboard)
    chanind/lmsys-chat-1m-qwen-2.5
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĵ¾æĿ¡
    -0.25
    [sizeof
    -0.23
    astered
    -0.23
    å¤ĸ壳
    -0.23
    稳
    -0.22
    çŃIJ
    -0.22
    æĮĤéĴ©
    -0.22
    .TODO
    -0.22
    InnerText
    -0.22
    åĸij
    -0.22
    POSITIVE LOGITS
    âļĹ
    0.37
     *</
    0.35
    -Mobile
    0.35
    bucks
    0.34
     (){
    0.34
    åĹIJ
    0.31
    -ves
    0.31
     cuckold
    0.31
    byn
    0.30
    errick
    0.30
    Activations Density 0.019%

    No Known Activations