© 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. 3177
    Prev
    Next
    INDEX
    Explanations

    technical reports

    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
    游æĪıæĵįä½ľ
    -0.24
     }}>{
    -0.24
    .AutoScaleMode
    -0.21
    <![
    -0.21
    å°ıç¼ĸä¸Ģèµ·
    -0.20
    WithContext
    -0.20
     Ñģдела
    -0.20
     withStyles
    -0.19
    yan
    -0.19
    .Low
    -0.19
    POSITIVE LOGITS
    mouseleave
    0.21
    pedia
    0.21
    .)↵↵↵↵
    0.20
    mouseenter
    0.19
    utenberg
    0.19
    ç³Ł
    0.18
    _DIST
    0.18
     despre
    0.18
     [=[
    0.18
    åĴ
    0.18
    Activations Density 0.001%

    No Known Activations