© 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. 2180
    Prev
    Next
    INDEX
    Explanations

    introduction and definitions

    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
    ,eg
    -0.22
     strugg
    -0.21
    /Dk
    -0.21
     Sesso
    -0.20
    veal
    -0.19
    -Semit
    -0.19
    odox
    -0.18
    /stdc
    -0.18
    *)_
    -0.18
     CONTRIBUT
    -0.18
    POSITIVE LOGITS
    Türkiye
    0.22
     Atatürk
    0.20
    mour
    0.20
    icers
    0.20
    createFrom
    0.20
     dicks
    0.20
    åĺĽ
    0.19
     badass
    0.19
    ymph
    0.19
    agnostic
    0.19
    Activations Density 0.002%

    No Known Activations