© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 505
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    DebugEnabled
    -0.42
    -0.39
     Unsure
    -0.36
    ChildIndex
    -0.36
    éĵ¨
    -0.35
    NavController
    -0.34
    æĺī
    -0.34
    èĽŃ
    -0.33
    OldData
    -0.33
    çıı
    -0.33
    POSITIVE LOGITS
    豪车
    0.63
    æĪķ
    0.56
    åªŀ
    0.54
    éĺ¿æł¹
    0.54
    éĩįè¦ģ举æݪ
    0.53
    å¥ĩ纳
    0.53
    å°±å¤Ł
    0.50
    èĻĵ
    0.50
    æĿ¨æ¬¢
    0.50
    ä¹Įåħĭ
    0.50
    Activations Density 24.369%

    No Known Activations