© 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. 1478
    Prev
    Next
    INDEX
    Explanations

    the

    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
    éļıæŶéļı
    -0.25
    __':č↵
    -0.25
    ":[{↵
    -0.23
    \/\/
    -0.22
    .SetParent
    -0.20
    itial
    -0.20
    ogenerated
    -0.20
    riors
    -0.20
    stown
    -0.20
    icamente
    -0.20
    POSITIVE LOGITS
     absence
    0.30
     midst
    0.29
     same
    0.28
     wake
    0.28
     past
    0.27
     meantime
    0.27
     vicinity
    0.26
     hope
    0.24
     context
    0.24
    wake
    0.24
    Activations Density 1.756%

    No Known Activations