© 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. 46330
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    ðŁĵIJ
    -0.27
    âļĹ
    -0.25
    (STD
    -0.22
    tti
    -0.21
    abcdefghijkl
    -0.21
    :absolute
    -0.20
    phin
    -0.20
     dope
    -0.20
     )))
    -0.20
    TableWidgetItem
    -0.20
    POSITIVE LOGITS
    dl
    0.21
     internally
    0.20
    à¸Ńม
    0.19
    çĥ©
    0.19
    illow
    0.18
    ermo
    0.18
    PLL
    0.18
    ogn
    0.18
    izard
    0.18
     intern
    0.18
    Activations Density 0.334%

    No Known Activations