© 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. 811
    Prev
    Next
    INDEX
    Explanations

    narrative plot points

    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
     hurd
    -0.26
     {?>↵
    -0.25
     uninsured
    -0.25
     companyName
    -0.25
    “(
    -0.25
     OpCode
    -0.24
     bigot
    -0.24
    “
    -0.24
     sodom
    -0.23
     vej
    -0.23
    POSITIVE LOGITS
    ç¾İåªĴ
    0.40
     pupper
    0.31
    Ḥ
    0.30
    åIJĸ
    0.29
    家éĥ½çŁ¥éģĵ
    0.28
    âĦħ
    0.28
    饸
    0.28
    /**↵↵
    0.27
    (Have
    0.27
     (;;
    0.27
    Activations Density 1.254%

    No Known Activations