© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1523
    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/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Animating
    -0.32
    Ũ
    -0.31
    либо
    -0.29
    Disappear
    -0.28
    imagin
    -0.28
    .AutoComplete
    -0.27
    è¹¼
    -0.27
    .userdetails
    -0.26
    çľ¼è¢ĭ
    -0.25
    ulfilled
    -0.25
    POSITIVE LOGITS
     libertin
    0.38
    RTOS
    0.32
    íĶĦë¡ľê·¸
    0.30
     perpetr
    0.30
    /Instruction
    0.28
     Erot
    0.27
     áll
    0.27
     ×Ķ×ķ×ĵ
    0.27
    UART
    0.27
    -Semit
    0.25
    Activations Density 9.173%

    No Known Activations