© 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. 873
    Prev
    Next
    INDEX
    Explanations

    code or text fragments

    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
    obierno
    -0.27
    =$('#
    -0.24
    ivitÃł
    -0.22
    getSimpleName
    -0.22
    abus
    -0.22
    å§ĭ建
    -0.20
    aleigh
    -0.20
    поÑĤенÑĨи
    -0.20
    ushman
    -0.20
    afür
    -0.20
    POSITIVE LOGITS
    irlines
    0.23
    idders
    0.21
    iens
    0.20
    åĺ´
    0.20
    æ¹ĵ
    0.19
    ABCDEFGHIJKLMNOP
    0.19
    FINITY
    0.19
    ussy
    0.18
    è·ı
    0.18
     inherit
    0.18
    Activations Density 0.001%

    No Known Activations