© 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. 2124
    Prev
    Next
    INDEX
    Explanations

    legal financial documents

    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
    elfast
    -0.23
     rencont
    -0.21
    derabad
    -0.20
    élection
    -0.18
    uden
    -0.18
    åħ¶ä»ĸçݩ家
    -0.18
    //{{
    -0.18
    UsageId
    -0.18
     zar
    -0.17
    .Are
    -0.17
    POSITIVE LOGITS
    rary
    0.26
     :";↵
    0.26
    ambre
    0.21
    onta
    0.21
     `}↵
    0.20
    (ConfigurationManager
    0.20
    ElementException
    0.20
     Ãĸnceki
    0.20
     Bugün
    0.20
    anela
    0.20
    Activations Density 0.001%

    No Known Activations