© 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. 46356
    Prev
    Next
    INDEX
    Explanations

    modelo

    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
     doPost
    -0.24
    declspec
    -0.23
    />.
    -0.22
    è·º
    -0.21
    ######↵
    -0.20
    %;">
    -0.20
    ä¸Ģèĩ´å¥½è¯Ħ
    -0.20
    ------+------+
    -0.19
    åı¯æĥ³èĢĮçŁ¥
    -0.19
    OMEM
    -0.19
    POSITIVE LOGITS
     **/č↵
    0.21
     ullam
    0.20
     antibiot
    0.20
     pregn
    0.20
     kull
    0.19
    oriously
    0.19
     fred
    0.19
     exercitation
    0.19
    /**↵↵
    0.19
     promin
    0.19
    Activations Density 0.013%

    No Known Activations