© 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. 402
    Prev
    Next
    INDEX
    Explanations

    and

    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
    管çIJĨåĴĮ
    -0.28
    ç»ıéªĮåĴĮ
    -0.24
    çIJĨ解åĴĮ
    -0.22
     ****************************************************************************
    -0.20
    antro
    -0.20
    /lg
    -0.19
    alyzed
    -0.19
    malı
    -0.19
    æĸĩåĮĸåĴĮ
    -0.19
    å¹³
    -0.18
    POSITIVE LOGITS
    /or
    0.70
    /OR
    0.43
    /of
    0.38
     other
    0.37
    rogen
    0.36
    åħ¶å®ĥ
    0.35
    rog
    0.32
     дÑĢÑĥгие
    0.32
    /o
    0.30
    èĶ¼
    0.29
    Activations Density 2.281%

    No Known Activations