© 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. 46645
    Prev
    Next
    INDEX
    Explanations

    code and data

    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
    ç½ħ
    -0.23
    enden
    -0.20
    ðŁİ¨
    -0.19
    ä¸Ĭå¹´åIJĮæľŁ
    -0.19
    hydrate
    -0.19
     REUTERS
    -0.19
    mts
    -0.18
    ä¾ĺ
    -0.18
     mest
    -0.18
    [++
    -0.18
    POSITIVE LOGITS
    }->
    0.21
     **/č↵
    0.21
    ca
    0.21
    ped
    0.21
    viewController
    0.20
    ĥģ
    0.20
    //[
    0.19
    ([]*
    0.18
    je
    0.18
    éķľ
    0.18
    Activations Density 0.092%

    No Known Activations