© 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. 383
    Prev
    Next
    INDEX
    Explanations

    copyright and licensing

    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
    ële
    -0.24
    .YELLOW
    -0.23
    ">//
    -0.22
    .onPause
    -0.22
     burge
    -0.21
    ormsg
    -0.21
    ä»Ĭ天å°ıç¼ĸ
    -0.20
     onPause
    -0.20
     mut
    -0.20
     '\''
    -0.20
    POSITIVE LOGITS
     sigu
    0.24
     acompaña
    0.24
     vå
    0.24
     vår
    0.22
    }()↵
    0.21
    æĢĿãĤı
    0.21
    ç«ij
    0.20
     fick
    0.20
     lå
    0.20
    stick
    0.20
    Activations Density 3.371%

    No Known Activations