© 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. 3001
    Prev
    Next
    INDEX
    Explanations

    names

    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
    ".↵↵↵↵
    -0.21
     Chapman
    -0.20
     Breed
    -0.20
    è¦ĭç©į
    -0.20
    gos
    -0.19
    æĭĤ
    -0.19
     NSObject
    -0.19
     comedic
    -0.18
    tingham
    -0.18
     UEFA
    -0.18
    POSITIVE LOGITS
    "w
    0.24
    èĶ¸
    0.21
    "in
    0.20
    ugins
    0.20
    :"-
    0.20
    Ø£ÙĪض
    0.19
    "f
    0.19
    \CMS
    0.19
    <path
    0.19
    зван
    0.18
    Activations Density 0.005%

    No Known Activations