© 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-65K
    7. 3842
    Prev
    Next
    INDEX
    Explanations

    code and 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
    gnore
    -0.23
    解æĶ¾æĢĿæĥ³
    -0.23
    åĻĻ
    -0.22
    åľ¨ç½ij绾
    -0.22
     gode
    -0.22
    able
    -0.21
    设计åĻ¨
    -0.21
    imately
    -0.21
    WAY
    -0.21
    Ĩ
    -0.20
    POSITIVE LOGITS
    serter
    0.26
    ÑģÑĤолÑĮ
    0.25
    regor
    0.24
    umberland
    0.24
    ’B
    0.24
     assh
    0.23
    /from
    0.23
    ãĤĴ缮
    0.23
    urrect
    0.22
    agements
    0.22
    Activations Density 0.502%

    No Known Activations