© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3870
    Prev
    Next
    INDEX
    Explanations

    adverbs ending in ly

    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
    )./
    -0.24
     RectTransform
    -0.22
    élection
    -0.21
    ",__
    -0.21
    uell
    -0.20
    ascript
    -0.20
    otland
    -0.20
    alance
    -0.20
     pestic
    -0.20
    lobal
    -0.19
    POSITIVE LOGITS
    è¦ģéĹ»
    0.25
    æ¾İæ¹ĥæĸ°éĹ»
    0.24
    缸åħ³æĸ°éĹ»
    0.24
    åĩ¤åĩ°ç½ij
    0.23
    ä¾ĿéĿł
    0.23
    ç¾İåªĴ
    0.22
    åıĸåĨ³
    0.22
    éĽĨä¸Ńåľ¨
    0.21
     responsible
    0.20
    éħIJ
    0.20
    Activations Density 0.248%

    No Known Activations