© 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. 984
    Prev
    Next
    INDEX
    Explanations

    Science and numbers

    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
    Specifier
    -0.22
    atisation
    -0.22
    )))),
    -0.21
    .CV
    -0.21
    ignum
    -0.20
    enaries
    -0.20
    usercontent
    -0.20
    etros
    -0.20
    ilage
    -0.20
    .scrollHeight
    -0.20
    POSITIVE LOGITS
     européen
    0.23
    è§ı
    0.22
    guarded
    0.21
    GameManager
    0.20
     Bair
    0.20
    >:</
    0.20
    ']]['
    0.19
    ess
    0.19
    æĹ¶ä»£ä¸ŃåĽ½
    0.19
     présenté
    0.19
    Activations Density 0.017%

    No Known Activations