© 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-65K
    7. 2899
    Prev
    Next
    INDEX
    Explanations

    technical code

    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
    :animated
    -0.34
    >'.↵
    -0.23
    豪车
    -0.23
     Oczy
    -0.22
     kommun
    -0.21
    è¸Ķ
    -0.21
    ().'/
    -0.20
    directive
    -0.20
    eggies
    -0.20
    åĬŁåĬ³
    -0.20
    POSITIVE LOGITS
    marginLeft
    0.22
    _pushButton
    0.22
     difÃŃc
    0.21
     Büyük
    0.19
    æĹģ
    0.19
     lesbienne
    0.18
    ogenerated
    0.18
    GLuint
    0.18
    ponsor
    0.18
     strncmp
    0.17
    Activations Density 0.007%

    No Known Activations