© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 608
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
    Âł
    -0.31
     "
    -0.25
    ↵
    -0.24
    ↵↵
    -0.22
    ³³
    -0.21
     **
    -0.21
    èģĶåĬ¨
    -0.21
    to
    -0.21
    ↵↵↵
    -0.21
    æľīåĪ©äºİ
    -0.21
    POSITIVE LOGITS
    -Cs
    0.34
    printStats
    0.32
    :'.$
    0.32
     addCriterion
    0.32
    æīĢæľīæĥħèĬĤ
    0.32
    esteem
    0.32
    âĦħ
    0.31
    ombine
    0.31
    .');č↵
    0.30
     Erectile
    0.30
    Activations Density 0.079%

    No Known Activations