© 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. 2516
    Prev
    Next
    INDEX
    Explanations

    technical contexts

    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
    ðŁĵIJ
    -0.25
    :'.$
    -0.24
    âļĹ
    -0.23
    lenmiÅŁ
    -0.22
    getStore
    -0.21
    %;"
    -0.21
    à¸Ńาà¸ģ
    -0.21
    ðŁĵĻ
    -0.20
    <t
    -0.20
    _Service
    -0.20
    POSITIVE LOGITS
     useHistory
    0.20
     malaysia
    0.19
    hir
    0.19
    éĨº
    0.19
    PropertyName
    0.19
    braska
    0.18
    JsonIgnore
    0.18
    模
    0.18
    vette
    0.18
     ConsoleColor
    0.18
    Activations Density 0.004%

    No Known Activations