© 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. 3072
    Prev
    Next
    INDEX
    Explanations

    reference numbers

    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
     strugg
    -0.23
    åİŁä¾Ĩ
    -0.23
    oldown
    -0.22
    éĥ¨åī¯
    -0.21
     RaisePropertyChanged
    -0.20
     acompaña
    -0.19
     cerco
    -0.19
    ArgumentException
    -0.19
     vej
    -0.19
    anford
    -0.19
    POSITIVE LOGITS
    鸪
    0.23
    orta
    0.21
    /orders
    0.21
    egl
    0.20
    ä½ĵåĬĽ
    0.19
    èį¨
    0.19
    Ñīин
    0.19
     ÑģенÑĤ
    0.19
    roph
    0.19
    ,SIGNAL
    0.19
    Activations Density 0.003%

    No Known Activations