© 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. 3293
    Prev
    Next
    INDEX
    Explanations

    publicMethod used: 1.Reason: MAX_ACTIVATING_TOKENS are all variations of the word "Public"

    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
    ecast
    -0.25
     (;;
    -0.24
     (;;)
    -0.24
    rchive
    -0.23
    ãİı
    -0.23
    âĪİ
    -0.23
    ä¹Įåħĭ
    -0.23
    bsolute
    -0.22
    åºij
    -0.22
     ↵↵
    -0.22
    POSITIVE LOGITS
    (public
    0.31
    -public
    0.27
    /public
    0.27
     pubb
    0.24
    -private
    0.24
     publicly
    0.24
    åħ¬å¼Ģ
    0.23
    -facing
    0.22
     navCtrl
    0.22
    public
    0.21
    Activations Density 0.106%

    No Known Activations