© 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. 146
    Prev
    Next
    INDEX
    Explanations

    acronyms

    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
    ,application
    -0.25
    ENCHMARK
    -0.23
    /Peak
    -0.23
    )NULL
    -0.22
    classnames
    -0.22
    .getContentPane
    -0.22
     prive
    -0.22
    buat
    -0.21
    LIK
    -0.21
     *)((
    -0.20
    POSITIVE LOGITS
     Kardash
    0.24
    P
    0.21
    F
    0.21
     {?}
    0.20
    W
    0.20
    G
    0.20
    ereotype
    0.20
    åĴ¦
    0.20
    å¨ģåIJį
    0.20
    O
    0.19
    Activations Density 1.974%

    No Known Activations