© 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. 2884
    Prev
    Next
    INDEX
    Explanations

    formatting emphasis

    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
    ÑĦеÑģÑģиона
    -0.26
     componentWill
    -0.24
     componentDidUpdate
    -0.22
     зай
    -0.21
     rumor
    -0.21
    "errors
    -0.20
     conte
    -0.20
    intptr
    -0.20
    æĿ¥çľĭçľĭåIJ§
    -0.19
    ç¾İèģĶ
    -0.19
    POSITIVE LOGITS
     sic
    0.30
    emphasis
    0.25
    nqu
    0.24
    .createFrom
    0.24
    ,{↵
    0.23
    .']
    0.23
     UsersController
    0.23
    ']]['
    0.22
    ASI
    0.22
    /Foundation
    0.22
    Activations Density 0.003%

    No Known Activations