© 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. 2880
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    æ¹İ
    -0.20
    éĢŀ
    -0.20
    çŁŃ线
    -0.20
    Äĩe
    -0.19
    'order
    -0.19
    .drawText
    -0.19
    RESSED
    -0.19
    blank
    -0.19
    owa
    -0.19
    @js
    -0.19
    POSITIVE LOGITS
    *)((
    0.29
    .createSequentialGroup
    0.23
    }}>↵
    0.22
    idebar
    0.22
    :]:↵
    0.21
    appen
    0.21
    #Region
    0.21
    aeda
    0.20
    .Sequential
    0.19
    lopedia
    0.19
    Activations Density 0.272%

    No Known Activations