© 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. 3788
    Prev
    Next
    INDEX
    Explanations

    technical code 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
    æĿ¥çľĭçľĭåIJ§
    -0.23
    次è¦ģ
    -0.20
    ç»ĵ
    -0.20
    (raw
    -0.19
     Sail
    -0.19
    æѤæ¡Ī
    -0.19
    _
    -0.18
     capac
    -0.18
    vider
    -0.18
    åħ¨éĿ¢å»ºæĪIJ
    -0.17
    POSITIVE LOGITS
    /GPL
    0.25
    AEA
    0.25
    );">↵
    0.24
    ÙħÙĪاÙĤÙģ
    0.24
     PureComponent
    0.23
    ennifer
    0.23
    -Origin
    0.23
    .AutoComplete
    0.22
    تخطÙĬØ·
    0.22
     CircularProgress
    0.22
    Activations Density 0.002%

    No Known Activations