© 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. 2895
    Prev
    Next
    INDEX
    Explanations

    score and score difference

    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
    çĮ¿
    -0.20
    kaar
    -0.20
    ,strlen
    -0.20
    -0.19
    yscale
    -0.19
    TED
    -0.19
     Spect
    -0.19
    æĪĺèĥľ
    -0.18
    /testify
    -0.18
    ä»Ĩ
    -0.18
    POSITIVE LOGITS
     halftime
    0.22
    ä¸Ģ度
    0.21
    æİĮæı¡äºĨ
    0.20
    equality
    0.19
    èħ§
    0.19
     donor
    0.19
    eworthy
    0.19
    ãĤ³ãĥ¼ãĥĴ
    0.18
     {!
    0.18
    åħ¨çIJĥ
    0.18
    Activations Density 0.144%

    No Known Activations