© 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. 1638
    Prev
    Next
    INDEX
    Explanations

    ease or advantage

    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
    åĿļå®ļä¸į
    -0.24
    _successful
    -0.22
     unsuccessfully
    -0.22
    åĬłåī§
    -0.21
    å¿ħä¸įåı¯
    -0.21
    å°İèĩ´
    -0.21
    toFloat
    -0.21
     slugg
    -0.21
    toDouble
    -0.21
    ä»İ严
    -0.21
    POSITIVE LOGITS
    æĹłéľĢ
    0.40
    æĸ¹ä¾¿
    0.38
    ä¸įçĶ¨
    0.35
    åıªéľĢ
    0.35
     easy
    0.35
     easily
    0.34
     without
    0.34
    ä¸įéľĢè¦ģ
    0.34
    便äºİ
    0.33
     unlike
    0.33
    Activations Density 6.640%

    No Known Activations