© 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. 521
    Prev
    Next
    INDEX
    Explanations

    word endings

    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
    esteem
    -0.30
    oling
    -0.25
    abus
    -0.24
    å°ıç¼ĸä¸Ģèµ·
    -0.23
    -Semit
    -0.22
    ">ÃĹ</
    -0.21
    grÃ¶ÃŁe
    -0.21
    (equalTo
    -0.21
    /↵↵↵↵
    -0.20
     CAUSED
    -0.20
    POSITIVE LOGITS
    ized
    0.22
    åĮĸ
    0.22
    ified
    0.22
    -friendly
    0.22
    patible
    0.21
    -
    0.20
    -era
    0.20
     getContext
    0.20
    friendly
    0.19
    /non
    0.19
    Activations Density 8.195%

    No Known Activations