© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 52
    Prev
    Next
    INDEX
    Explanations

    almost or nearly

    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
    cestor
    -0.22
    textAlign
    -0.20
     probably
    -0.20
    èĩ³å°ij
    -0.19
    SizePolicy
    -0.19
     Borough
    -0.19
    é¾ĻéŨ
    -0.18
    alties
    -0.18
     basically
    -0.18
    ÑģколÑĮко
    -0.18
    POSITIVE LOGITS
    etxt
    0.32
     guarante
    0.27
    ottage
    0.26
    pard
    0.26
    onium
    0.25
    upertino
    0.24
    ]]];↵
    0.24
    engeance
    0.24
    upported
    0.24
    ingleton
    0.23
    Activations Density 1.387%

    No Known Activations