© 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. 3302
    Prev
    Next
    INDEX
    Explanations

    technical text

    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
    ,},↵
    -0.20
    warts
    -0.19
    -inf
    -0.19
    /th
    -0.19
    mainwindow
    -0.19
     genie
    -0.18
     Inf
    -0.18
     Democratic
    -0.18
    anke
    -0.18
    izabeth
    -0.18
    POSITIVE LOGITS
    .scalablytyped
    0.23
    ">ÃĹ</
    0.22
    åĻĮ
    0.21
    ết
    0.21
    EmptyEntries
    0.21
    åĹIJ
    0.20
    ðŁĶĹ
    0.20
    ">//
    0.20
    å§ĭ建
    0.20
    chia
    0.20
    Activations Density 0.001%

    No Known Activations