© 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. 1968
    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
    åıĪ好
    -0.25
    ]={↵
    -0.21
     fkk
    -0.20
    å·¨æĺŁ
    -0.20
    ]='\
    -0.20
    alfa
    -0.19
    .VisualBasic
    -0.19
    zyst
    -0.19
    .getUserName
    -0.19
    ä¸īæĸ¹
    -0.19
    POSITIVE LOGITS
    -lfs
    0.21
    ActionCreators
    0.21
    åºŃ
    0.20
    sexo
    0.20
     pract
    0.20
    ëªĩ
    0.19
    åħ¶å®ĥéĹ®é¢ĺ
    0.19
    customerId
    0.19
     relu
    0.19
    æīİ
    0.18
    Activations Density 0.001%

    No Known Activations