© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1398
    Prev
    Next
    INDEX
    Explanations

    scientific detection and analysis

    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
    --[[
    -0.29
    ,module
    -0.26
    observeOn
    -0.26
     (!((
    -0.26
     Porno
    -0.25
     Pornhub
    -0.25
     safezone
    -0.24
     tbsp
    -0.24
     practition
    -0.24
    á¹Ģ
    -0.24
    POSITIVE LOGITS
    åºĶæĶ¶è´¦
    0.27
     jewish
    0.27
     roma
    0.26
    ä½ıæĪ¿åħ¬ç§¯
    0.26
     erotica
    0.26
    IFn
    0.24
     personals
    0.24
    äºĨè¿ĩæĿ¥
    0.24
     algu
    0.24
    建档ç«ĭ
    0.23
    Activations Density 4.641%

    No Known Activations