© 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-CHAT-65K
    7. 46062
    Prev
    Next
    INDEX
    Explanations

    0

    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/lmsys/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 192 tokens each
    Dataset (Dashboard)
    chanind/lmsys-chat-1m-qwen-2.5
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    太快
    -0.20
    çªľ
    -0.19
    建档ç«ĭ
    -0.19
     rak
    -0.19
    ught
    -0.18
     rencontres
    -0.18
     gratuits
    -0.18
    çijķ
    -0.18
    TestCase
    -0.18
    å§ĺ
    -0.17
    POSITIVE LOGITS
    benh
    0.27
    :request
    0.23
    éparation
    0.22
    mbH
    0.22
    ábado
    0.21
    ographed
    0.21
    ngr
    0.21
    vertisement
    0.20
    buch
    0.20
    /TR
    0.20
    Activations Density 0.027%

    No Known Activations