© 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. 1505
    Prev
    Next
    INDEX
    Explanations

    anatomy body parts

    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
     userEmail
    -0.30
     confirmPassword
    -0.30
     emailAddress
    -0.25
    toFloat
    -0.24
     ecl
    -0.24
     gridView
    -0.23
    åĻİ
    -0.22
    (<?
    -0.21
    -facebook
    -0.21
    íĬ¹ë³Ħ
    -0.21
    POSITIVE LOGITS
    å¼Ģå¥ĸç»ĵæŀľ
    0.28
    éĥ¨ä½į
    0.28
    ﹤
    0.28
    bove
    0.27
    /↵↵↵↵
    0.26
    /umd
    0.25
    ç»ıå¼Ģ
    0.25
     (*((
    0.25
    ä½Ĩä¸įéĻIJ
    0.25
    æ¯ĹéĤ»
    0.25
    Activations Density 6.470%

    No Known Activations