© 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. 1867
    Prev
    Next
    INDEX
    Explanations

    specific items or actions

    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
     activeClassName
    -0.25
    æį¢åı¥è¯Ŀ
    -0.22
    getMock
    -0.22
     fête
    -0.22
    pliant
    -0.21
    ihan
    -0.21
    ceipt
    -0.21
     propriété
    -0.21
    sembling
    -0.21
     Hindered
    -0.21
    POSITIVE LOGITS
    ]={↵
    0.20
    -Methods
    0.20
    .val
    0.19
    empre
    0.19
    trzym
    0.18
    âĩ§
    0.18
    ãģ¦ãģĦãģįãģŁãģĦ
    0.18
     PhpStorm
    0.18
     high
    0.18
     (!((
    0.18
    Activations Density 0.548%

    No Known Activations