© 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. 3436
    Prev
    Next
    INDEX
    Explanations

    services and solutions

    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
    kür
    -0.20
    çĶ¨å¾®ä¿¡
    -0.20
    dzi
    -0.20
    SelfPermission
    -0.20
    ÎĦ
    -0.19
    isOk
    -0.19
    ensex
    -0.19
     !");↵
    -0.18
    .requireNonNull
    -0.18
    è°¶
    -0.18
    POSITIVE LOGITS
    etxt
    0.23
    macen
    0.22
    erties
    0.21
    æ±Ĩ
    0.21
    ä¸Ģèĩ´å¥½è¯Ħ
    0.21
     lorem
    0.21
    çĭĴ
    0.19
    zure
    0.19
    inned
    0.18
    afür
    0.18
    Activations Density 0.001%

    No Known Activations