© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1097
    Prev
    Next
    INDEX
    Explanations

    Dates and 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
    ardu
    -0.25
    uale
    -0.24
    errated
    -0.24
    kea
    -0.23
    bsolute
    -0.23
    alink
    -0.23
    ILLISE
    -0.22
    )↵↵↵↵↵↵↵↵
    -0.22
    vla
    -0.21
    qus
    -0.21
    POSITIVE LOGITS
    .for
    0.21
    游æĪıè§Ĵèī²
    0.21
     fontStyle
    0.20
    å¹´ä¹ĭ
    0.20
    :'',
    0.19
    .getExternalStorage
    0.19
    @show
    0.18
    iber
    0.18
    åı¯æĥ³èĢĮçŁ¥
    0.18
    stit
    0.18
    Activations Density 1.057%

    No Known Activations