© 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. 2995
    Prev
    Next
    INDEX
    Explanations

    evolution and selection

    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
    大åŀĭå¤ļ人
    -0.28
    /Dk
    -0.26
    ï¹ı
    -0.23
    aeda
    -0.22
     nomine
    -0.22
    åħļçļĦåįģ
    -0.21
     @$_
    -0.20
    椴
    -0.20
    cket
    -0.20
    æĢ»èĢĮè¨Ģ
    -0.20
    POSITIVE LOGITS
     evolutionary
    0.27
    çĶŁåŃĺ
    0.26
    è¿ĽåĮĸ
    0.24
     Evolution
    0.23
     survival
    0.22
     Sloan
    0.21
    ç¥ĸåħĪ
    0.21
    æ¼ĶåĮĸ
    0.21
     evolution
    0.20
    oca
    0.20
    Activations Density 0.378%

    No Known Activations