© 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. 1988
    Prev
    Next
    INDEX
    Explanations

    specific text segments

    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
     CORPOR
    -0.28
    -initialized
    -0.27
    yectos
    -0.27
    ialized
    -0.26
    irectory
    -0.24
    ujet
    -0.24
    esktop
    -0.23
    iguiente
    -0.23
    gregar
    -0.23
    ayette
    -0.23
    POSITIVE LOGITS
    è¹ļ
    0.28
    çīĪæĿĥå½Ĵ
    0.27
    âĬĦ
    0.26
    TestId
    0.26
    å¿ħä¸įåı¯
    0.25
    0.24
    (COLOR
    0.24
    ungalow
    0.22
    带æĿ¥æĽ´å¤ļ
    0.22
    æĿ¥çľĭçľĭåIJ§
    0.22
    Activations Density 1.422%

    No Known Activations