© 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. 2609
    Prev
    Next
    INDEX
    Explanations

    reasons

    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
    ICTURE
    -0.27
    istrator
    -0.24
    üssen
    -0.24
    oriously
    -0.23
     occas
    -0.23
     rencont
    -0.22
    âĸ¹
    -0.22
    ilmington
    -0.22
     enthus
    -0.21
     oppon
    -0.21
    POSITIVE LOGITS
    ulumi
    0.21
    ing
    0.21
     ofApp
    0.20
    ab
    0.20
    ç½¢
    0.20
    ickerView
    0.19
    engu
    0.19
    er
    0.19
    .INVISIBLE
    0.18
    ().'/
    0.18
    Activations Density 0.024%

    No Known Activations