© 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. 3767
    Prev
    Next
    INDEX
    Explanations

    positive sentiment

    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
    çİ¢
    -0.20
    izedName
    -0.20
    /**↵↵
    -0.19
    éĶ¥
    -0.19
    vat
    -0.18
    æķ°çłģ
    -0.18
    纰
    -0.18
     "(\<
    -0.18
    èĪ·
    -0.17
    iddleware
    -0.17
    POSITIVE LOGITS
    }());↵
    0.24
     helf
    0.22
    -Jul
    0.22
     gameTime
    0.22
    ($('<
    0.21
    ﹤
    0.20
    èĴº
    0.20
    uelles
    0.20
    gings
    0.20
     Erot
    0.20
    Activations Density 0.345%

    No Known Activations