© 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. 2162
    Prev
    Next
    INDEX
    Explanations

    administrative or formal texts

    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
    ERRU
    -0.24
    engkap
    -0.22
    kek
    -0.22
    ç°Ł
    -0.21
     Jeżeli
    -0.21
     Trafford
    -0.20
    ìĸµ
    -0.20
    YSTEM
    -0.19
    äºīåĪĽ
    -0.19
    <Transform
    -0.19
    POSITIVE LOGITS
    çļĦç§ĺå¯Ĩ
    0.19
     svenska
    0.19
     Casinos
    0.19
    ç³ľ
    0.19
    ATAR
    0.18
    骨头
    0.18
    ç¼Į
    0.18
    .bio
    0.18
    .?
    0.18
    èīĩ
    0.18
    Activations Density 0.002%

    No Known Activations