© 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. 1991
    Prev
    Next
    INDEX
    Explanations

    .

    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
    ëĴ¤
    -0.19
    bucks
    -0.19
     PÃ¥
    -0.19
    ={"/
    -0.19
    姹
    -0.18
    éĶĴ
    -0.18
    çIJ¬
    -0.18
     ÙĬÙĪÙĦ
    -0.18
    BASEPATH
    -0.18
    clearfix
    -0.18
    POSITIVE LOGITS
    (SQLException
    0.23
    )const
    0.22
    andles
    0.21
    hetto
    0.21
    otonin
    0.21
    roupon
    0.21
    caler
    0.20
    oundary
    0.20
    omething
    0.20
     lParam
    0.20
    Activations Density 0.895%

    No Known Activations