© 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. 1480
    Prev
    Next
    INDEX
    Explanations

    diverse technical terms

    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
    <path
    -0.21
     Leigh
    -0.20
    TargetException
    -0.19
    <fieldset
    -0.19
    çĬ·
    -0.18
    ulings
    -0.18
    .Ticks
    -0.18
    æģ«
    -0.18
    æ²īæµ¸åľ¨
    -0.18
    宬
    -0.18
    POSITIVE LOGITS
     Decompiled
    0.23
    è§ĨåIJ¬èĬĤ缮
    0.22
    ëĵ¦
    0.21
    对åħ¶çľŁå®ŀ
    0.21
    ,},↵
    0.20
    irebase
    0.20
    æĹ´
    0.20
    Ụ
    0.20
     Crushers
    0.20
    =?",
    0.20
    Activations Density 0.001%

    No Known Activations