© 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. 2996
    Prev
    Next
    INDEX
    Explanations

    product 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
    áIJī
    -0.32
    bsolute
    -0.32
    áIJĪ
    -0.32
    âļĹ
    -0.31
    nqu
    -0.31
    incinn
    -0.31
    lijah
    -0.30
    ifestyles
    -0.29
    uxtap
    -0.28
    .cloudflare
    -0.28
    POSITIVE LOGITS
    ç§ijçłĶéĻ¢
    0.23
    æĸ°éĹ»ä¸Ńå¿ĥ
    0.23
    åħ¨åªĴä½ĵ
    0.21
     kaps
    0.21
    缸åħ³æĸ°éĹ»
    0.21
     addons
    0.21
     scor
    0.21
    综èīºèĬĤ缮
    0.20
     assort
    0.20
    ÑĥÑģÑĤÑĢой
    0.20
    Activations Density 1.849%

    No Known Activations