© 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. 2395
    Prev
    Next
    INDEX
    Explanations

    technical/scientific notation

    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
    ]string
    -0.22
    hiba
    -0.22
     ontvang
    -0.19
    /MIT
    -0.19
    charger
    -0.19
    agine
    -0.19
    æĮĿ
    -0.19
    .navigateByUrl
    -0.18
    *g
    -0.18
     eros
    -0.18
    POSITIVE LOGITS
    å¤ļéĩį
    0.22
    æĹłè®ºæĺ¯åħ¶
    0.21
    ummings
    0.21
    æĸĩåĮĸèĬĤ
    0.20
    desktop
    0.19
    奥æŀĹåĮ¹
    0.19
    éĩįè¦ģ举æݪ
    0.19
    ixo
    0.19
    MUX
    0.19
    (#)
    0.19
    Activations Density 0.030%

    No Known Activations