© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3688
    Prev
    Next
    INDEX
    Explanations

    specific entities

    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
    invert
    -0.21
    å¦Ĭ
    -0.21
    âĩij
    -0.20
    ndl
    -0.20
    -te
    -0.19
    trak
    -0.19
    kea
    -0.19
    .FileNotFoundException
    -0.19
    iveau
    -0.19
    个çĻ¾åĪĨ
    -0.19
    POSITIVE LOGITS
    窸
    0.24
    ØŃتÙĬاج
    0.22
    -validate
    0.21
     }}"><
    0.21
    å¨ĵ
    0.20
     boobs
    0.19
     Deze
    0.19
    æ°ª
    0.19
    ä¸ī个æĸ¹éĿ¢
    0.19
    å¢ħ
    0.19
    Activations Density 0.002%

    No Known Activations