© 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. 832
    Prev
    Next
    INDEX
    Explanations

    calculus and math

    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
    è°¢éĤĢ
    -0.38
     philippines
    -0.28
     Fucking
    -0.26
     Bitcoins
    -0.26
    ðŁĮ°
    -0.25
    _VIRTUAL
    -0.25
     Buccane
    -0.24
    leftright
    -0.24
     jihadist
    -0.24
     jihadists
    -0.24
    POSITIVE LOGITS
    "testing
    0.28
    @update
    0.26
    ":[{↵
    0.25
    ",__
    0.25
    "path
    0.25
    åŃ½
    0.24
    "sync
    0.23
    æijģ
    0.23
    [it
    0.23
    .ErrorCode
    0.23
    Activations Density 2.909%

    No Known Activations