© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1440
    Prev
    Next
    INDEX
    Explanations

    lawsuits

    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
     imgUrl
    -0.26
     erotica
    -0.25
    çŀŁ
    -0.23
     upbeat
    -0.21
    opian
    -0.20
     offender
    -0.20
    à¹Ģà¸ĸ
    -0.20
     ntohs
    -0.20
    ereotype
    -0.20
     ?>>
    -0.20
    POSITIVE LOGITS
    æıIJèµ·
    0.31
    #ga
    0.25
     claims
    0.24
    "},{"
    0.23
    èµ·è¯ī
    0.23
    ç¼ł
    0.23
    æĬķè¯ī
    0.23
    ç«ĭæ¡Ī
    0.23
     claim
    0.22
    ,");↵
    0.22
    Activations Density 1.716%

    No Known Activations