© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-CHAT-65K
    7. 45776
    Prev
    Next
    INDEX
    Explanations

    code and language

    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
    íıIJ
    -0.21
    .loggedIn
    -0.21
    使人
    -0.21
    .isLoggedIn
    -0.20
    *)_
    -0.19
    .gray
    -0.19
    ographed
    -0.19
    assadors
    -0.19
    ä»Ģ麽
    -0.19
    ãĤĭãĤĤãģ®
    -0.19
    POSITIVE LOGITS
    rous
    0.22
    defgroup
    0.21
    xFFFFFF
    0.19
    ihanna
    0.19
    ä¸īæĿ¡
    0.19
     bara
    0.19
    ulong
    0.19
    )did
    0.18
    eenth
    0.18
    ney
    0.18
    Activations Density 0.001%

    No Known Activations