© 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. 1492
    Prev
    Next
    INDEX
    Explanations

    academic context

    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
    impse
    -0.24
    OrFail
    -0.22
    ,assign
    -0.21
    çļĦ带é¢Ĩ
    -0.21
    .MouseAdapter
    -0.21
    (___
    -0.21
    .chomp
    -0.21
    _FAULT
    -0.20
    ,readonly
    -0.20
    {return
    -0.20
    POSITIVE LOGITS
    /AFP
    0.20
     helf
    0.20
    SnackBar
    0.20
     spel
    0.19
     embod
    0.19
     isAdmin
    0.19
    -Pack
    0.19
    "go
    0.19
    ðŁ¥£
    0.18
    uppen
    0.18
    Activations Density 0.124%

    No Known Activations