© 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. 2910
    Prev
    Next
    INDEX
    Explanations

    business or technical

    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
    §è¡Į
    -0.23
     eget
    -0.22
    æ¡ĵ
    -0.20
    ÙĨÙħÙĪØ°
    -0.20
    深度
    -0.20
    ections
    -0.20
    å°¾
    -0.20
    edin
    -0.19
    hos
    -0.19
    haust
    -0.19
    POSITIVE LOGITS
    æĹłäºº
    0.20
    骸
    0.20
     setFrame
    0.20
    setOnClickListener
    0.20
    peria
    0.19
     Chr
    0.19
    ampionship
    0.18
    vae
    0.18
     #=>
    0.18
    ouflage
    0.18
    Activations Density 0.002%

    No Known Activations