© 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. 3040
    Prev
    Next
    INDEX
    Explanations

    court case filings

    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
     UIScreen
    -0.25
    buat
    -0.24
    /ion
    -0.20
    _peng
    -0.20
    .AppendFormat
    -0.20
    ëĸ»
    -0.20
    æĿ³
    -0.20
     california
    -0.20
    ḿ
    -0.19
    .readValue
    -0.19
    POSITIVE LOGITS
    ðŁ¤ĸ
    0.20
    éĥ¸
    0.20
    åĴĮå¹³
    0.20
    å¾Ń
    0.19
    ä»İ严治
    0.19
     Folk
    0.19
    Multiplier
    0.19
    поÑĤенÑĨи
    0.19
    <<
    0.19
    çIJĽ
    0.19
    Activations Density 0.227%

    No Known Activations