© 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. 1904
    Prev
    Next
    INDEX
    Explanations

    contributed equally

    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
     ofApp
    -0.22
     traged
    -0.20
    apping
    -0.20
     blockDim
    -0.20
    serialization
    -0.19
     expectedResult
    -0.19
     ìĺĪ
    -0.19
    æīĢ说çļĦ
    -0.19
     perÃŃ
    -0.18
    erra
    -0.18
    POSITIVE LOGITS
    ëĸĦ
    0.27
    éĶµ
    0.26
    sexy
    0.24
    è·¹
    0.23
    ï¼ĩ
    0.23
    ï¼ģ",
    0.23
    }elseif
    0.22
    ;/*
    0.22
    次è¦ģ
    0.22
    ToBounds
    0.21
    Activations Density 0.324%

    No Known Activations