© 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. 1129
    Prev
    Next
    INDEX
    Explanations

    code copyright

    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
     ×Ķ×ķ×ĵ
    -0.23
     AssemblyDescription
    -0.23
    IGHLIGHT
    -0.22
    åĬłçĽŁåºĹ
    -0.22
    krÄĻ
    -0.21
    ibri
    -0.19
    (*)(
    -0.19
    poly
    -0.19
    ederland
    -0.19
    为æĬĵ
    -0.19
    POSITIVE LOGITS
     (*((
    0.24
    :animated
    0.23
    åľ°ä¸Ń
    0.21
    æħ
    0.20
    æ½Ń
    0.20
    webElementProperties
    0.20
    gere
    0.20
    ames
    0.20
    cec
    0.19
    tokenId
    0.19
    Activations Density 1.424%

    No Known Activations