© 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. 411
    Prev
    Next
    INDEX
    Explanations

    word 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
    'icon
    -0.23
    åķ»
    -0.22
    serter
    -0.21
    ฤษ
    -0.21
    oproject
    -0.20
    Descricao
    -0.20
     blowjob
    -0.20
    uckland
    -0.20
     einzel
    -0.20
    aneously
    -0.20
    POSITIVE LOGITS
    ctrine
    0.35
    gnore
    0.29
    åIJĦæł·
    0.28
    ÑįÑĤомÑĥ
    0.27
    iá»ĩn
    0.27
    IGINAL
    0.26
    apons
    0.26
    etheless
    0.26
    YSTEM
    0.26
    jourd
    0.26
    Activations Density 5.350%

    No Known Activations