© 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. 734
    Prev
    Next
    INDEX
    Explanations

    introduction sections

    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
     createAction
    -0.22
    .Localization
    -0.21
     consect
    -0.20
    rang
    -0.19
     Vall
    -0.18
    AccessException
    -0.18
    å£ħ
    -0.18
    .ToLower
    -0.18
    );}↵
    -0.18
     TInt
    -0.18
    POSITIVE LOGITS
    -Cs
    0.24
    UTERS
    0.22
    :";č↵
    0.21
    å»ĭ
    0.21
    ıl
    0.20
    /books
    0.20
     Chamber
    0.19
    extrême
    0.19
    isson
    0.19
    isclosed
    0.19
    Activations Density 0.011%

    No Known Activations