© 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. 1896
    Prev
    Next
    INDEX
    Explanations

    Microsoft programming

    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
    NamedQuery
    -0.29
    /Instruction
    -0.25
    opportunitÃł
    -0.25
    .CustomButton
    -0.24
    .FindGameObjectWithTag
    -0.24
     FontStyle
    -0.22
    BuilderInterface
    -0.22
    .RowStyle
    -0.22
    åįĴ
    -0.22
    GetMethod
    -0.21
    POSITIVE LOGITS
    .aspx
    0.34
     Microsoft
    0.28
    .asp
    0.26
    Microsoft
    0.25
    .microsoft
    0.24
    缸åħ³è´Łè´£
    0.23
    axies
    0.22
     kull
    0.22
     clr
    0.22
    åIJįåĪĹ
    0.22
    Activations Density 4.091%

    No Known Activations