© 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. 670
    Prev
    Next
    INDEX
    Explanations

    code elements

    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
     onAnimation
    -0.28
    -prepend
    -0.23
     mouseClicked
    -0.22
     setBackgroundColor
    -0.21
     radioButton
    -0.21
     gridColumn
    -0.21
     setBackground
    -0.21
    erson
    -0.21
     erotica
    -0.20
     strtol
    -0.20
    POSITIVE LOGITS
    æĭľå¸ĪåѦ
    0.29
    ,");↵
    0.29
    "value
    0.27
    "data
    0.27
    \application
    0.27
    __;↵
    0.26
     Ä°zmir
    0.25
    ,No
    0.25
    -Methods
    0.25
    ðŁĵIJ
    0.25
    Activations Density 0.261%

    No Known Activations