© 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. 2344
    Prev
    Next
    INDEX
    Explanations

    proportions and ratios

    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
    :"<<
    -0.22
    /epl
    -0.21
    对æİ¥
    -0.20
    缴è¾ĸ
    -0.19
    ]={↵
    -0.19
    loth
    -0.19
    ower
    -0.19
    æľĶ
    -0.19
    -License
    -0.18
     POLITICO
    -0.18
    POSITIVE LOGITS
    æ¯Ķä¾ĭ
    0.62
     ratio
    0.60
    åįłæ¯Ķ
    0.56
    çļĦæ¯Ķä¾ĭ
    0.56
     ratios
    0.56
     proportions
    0.55
    ratio
    0.54
     balance
    0.54
    平衡
    0.53
     Ratio
    0.51
    Activations Density 0.606%

    No Known Activations