© 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. 1626
    Prev
    Next
    INDEX
    Explanations

    code and math

    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
    ÑĤи
    -0.20
    ¹Ħ
    -0.19
     Silicon
    -0.19
    issions
    -0.19
    endencies
    -0.19
    æłī
    -0.19
    iblings
    -0.19
     Backpack
    -0.18
    ollider
    -0.18
    jak
    -0.18
    POSITIVE LOGITS
    Ascii
    0.22
    .NaN
    0.22
    ->{_
    0.21
    enticated
    0.21
    ToBounds
    0.20
    DOMNode
    0.20
    неÑģен
    0.20
    _ascii
    0.20
    elay
    0.20
    UILTIN
    0.20
    Activations Density 0.373%

    No Known Activations