© 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. 2094
    Prev
    Next
    INDEX
    Explanations

    word fragments

    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
     randomNumber
    -0.20
    æ³ķ
    -0.20
    æĶ¾
    -0.19
    .Popup
    -0.19
    aternion
    -0.19
    两åıª
    -0.19
    ripp
    -0.19
    _lbl
    -0.18
    ingleton
    -0.18
     Starr
    -0.18
    POSITIVE LOGITS
    .MaximizeBox
    0.24
    ynthia
    0.23
    ä¸ĭéĿ¢æĺ¯å°ı
    0.23
    æ¡·
    0.23
    ç»ī
    0.23
    |array
    0.22
    åĹ²
    0.22
    âĦī
    0.21
    èį¸
    0.21
     سبØŃ
    0.21
    Activations Density 0.001%

    No Known Activations