© 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. 2797
    Prev
    Next
    INDEX
    Explanations

    specific items or queries

    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
    memberOf
    -0.21
    élection
    -0.20
    ожеÑĤ
    -0.20
     didFinish
    -0.20
    avanaugh
    -0.20
    abay
    -0.19
    âı³
    -0.19
    ðŁ¥ĩ
    -0.19
    ruc
    -0.18
    æĴ¥
    -0.18
    POSITIVE LOGITS
     adulti
    0.23
     demi
    0.21
    ä½ıæĪ¿åħ¬ç§¯
    0.20
    窸
    0.20
    åľ¨è¿ĩ渡
    0.19
     andre
    0.18
    oggler
    0.18
    èīĦ
    0.18
     prive
    0.17
    Ä±ÅŁÄ±
    0.17
    Activations Density 0.001%

    No Known Activations