© 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. 2515
    Prev
    Next
    INDEX
    Explanations

    categories/headings

    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
    èµĻ
    -0.27
    esis
    -0.24
    积
    -0.21
    )&&(
    -0.19
    ksam
    -0.19
    èµĤ
    -0.19
     Heights
    -0.19
    |unique
    -0.19
    edith
    -0.18
    plevel
    -0.18
    POSITIVE LOGITS
    )init
    0.24
    >*/↵
    0.23
    大大å°ı
    0.20
     Metodo
    0.20
    statt
    0.19
     Bun
    0.19
    åIJİæİĴ
    0.19
    /colors
    0.19
    iera
    0.19
    ahoo
    0.19
    Activations Density 0.001%

    No Known Activations