© 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. 46685
    Prev
    Next
    INDEX
    Explanations

    enable/disable

    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
    /Dk
    -0.26
    swire
    -0.25
    |--------------------------------------------------------------------------↵
    -0.23
    lijah
    -0.22
    iless
    -0.21
     !***
    -0.21
    <tag
    -0.20
     Decompiled
    -0.20
    EventData
    -0.20
    -With
    -0.19
    POSITIVE LOGITS
    ourage
    0.21
     FString
    0.21
    è£
    0.20
    ãģĨãģĵãģ¨
    0.20
     zob
    0.19
    åĪĢ
    0.19
    è´´
    0.19
     ObjectOutputStream
    0.18
    .isLoggedIn
    0.18
     caz
    0.18
    Activations Density 0.036%

    No Known Activations