© 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. 3488
    Prev
    Next
    INDEX
    Explanations

    web addresses

    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
     incontri
    -0.21
    afür
    -0.21
    aturdays
    -0.20
    ḷ
    -0.20
    jährige
    -0.19
     francaise
    -0.19
    ábado
    -0.19
    åij¸
    -0.19
    æģļ
    -0.19
    ugi
    -0.19
    POSITIVE LOGITS
    黩
    0.21
    :CGRect
    0.21
    åĮħåĮħ
    0.20
    å¸Ķ
    0.20
    åĴį
    0.19
    .gameObject
    0.19
     +=↵
    0.19
    chimp
    0.19
    ÐŁÐ¾Ð´ÑĢоб
    0.19
    agate
    0.18
    Activations Density 0.480%

    No Known Activations