© 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. 2731
    Prev
    Next
    INDEX
    Explanations

    url parts

    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
    cratch
    -0.22
     gar
    -0.21
    .InnerText
    -0.20
    çĹ«
    -0.20
    =plt
    -0.20
    traction
    -0.20
     erotica
    -0.19
    afür
    -0.19
    踹
    -0.19
    饯
    -0.18
    POSITIVE LOGITS
     volunte
    0.27
    )((((
    0.23
    çIJĽ
    0.23
    .scalablytyped
    0.22
    游æĪıå½ĵä¸Ń
    0.22
    phalt
    0.22
    å±Ĥåĩºä¸į
    0.22
     CORPOR
    0.21
    szed
    0.21
    *>*
    0.21
    Activations Density 0.069%

    No Known Activations