© 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. 3258
    Prev
    Next
    INDEX
    Explanations

    governance and stability

    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
     solidarity
    -0.22
    whelming
    -0.21
    åĴĮæľįåĬ¡
    -0.21
    erland
    -0.20
    缴å±ŀ
    -0.19
     declaración
    -0.19
     centerX
    -0.18
     jihadist
    -0.18
    æķķ
    -0.18
    oid
    -0.18
    POSITIVE LOGITS
    curacy
    0.24
     Transparency
    0.23
    herits
    0.23
    诳
    0.22
    åĶIJå®ĩ
    0.22
    ]={↵
    0.21
    çݩ家æľĭåıĭ
    0.21
     FindObjectOfType
    0.21
    arat
    0.21
    人æĿĥ
    0.21
    Activations Density 0.465%

    No Known Activations