© 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. 1212
    Prev
    Next
    INDEX
    Explanations

    email or date format

    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
    rescia
    -0.30
    _Tick
    -0.22
     applyMiddleware
    -0.22
    ÐŁÐ¾Ð´ÑĢобнее
    -0.22
    ushman
    -0.21
    põe
    -0.21
    .HOUR
    -0.21
    .oc
    -0.21
     ámb
    -0.21
    },${
    -0.21
    POSITIVE LOGITS
    -era
    0.24
     francais
    0.24
    -present
    0.23
    -Jan
    0.22
     edition
    0.21
    ëħĦ
    0.21
    ä¸ĵä¸ļä»İäºĭ
    0.20
    textTheme
    0.20
    年第
    0.20
    RectTransform
    0.20
    Activations Density 0.812%

    No Known Activations