© 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. 3286
    Prev
    Next
    INDEX
    Explanations

    code keywords

    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
    icone
    -0.24
    ]int
    -0.23
    -Cs
    -0.22
    élection
    -0.21
     GANG
    -0.21
    æĢ§ä»·
    -0.21
     ofApp
    -0.20
     uten
    -0.20
    âĩĵ
    -0.20
    /Instruction
    -0.20
    POSITIVE LOGITS
    è¯İ
    0.21
    ierz
    0.20
     [&](
    0.19
    å¼ĢæĿ¥
    0.19
     "&#
    0.18
    case
    0.18
    æĿ¥è¯´
    0.18
     btnSave
    0.18
    为æŃ¢
    0.18
    åĢĴ
    0.18
    Activations Density 0.007%

    No Known Activations