© 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. 969
    Prev
    Next
    INDEX
    Explanations

    probability chance risk

    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
     "%"
    -0.20
    NSS
    -0.20
    uxtap
    -0.19
    oder
    -0.18
    resolver
    -0.18
    ent
    -0.17
    æѦ
    -0.17
     Maid
    -0.17
    BackPressed
    -0.17
    DMETHOD
    -0.17
    POSITIVE LOGITS
     chance
    0.29
    uggage
    0.24
    allest
    0.24
    elize
    0.23
    -Methods
    0.23
    elihood
    0.23
     Chance
    0.21
    ilmington
    0.21
    rvine
    0.21
    .slim
    0.21
    Activations Density 1.344%

    No Known Activations