© 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. 2343
    Prev
    Next
    INDEX
    Explanations

    specific nouns

    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
    ç¿İ
    -0.19
    åī¯
    -0.19
    iance
    -0.18
     Shed
    -0.18
    ãĦ´
    -0.18
    Çľ
    -0.17
    UITableView
    -0.17
    ume
    -0.17
    umer
    -0.17
    iÅŁ
    -0.17
    POSITIVE LOGITS
    åģ»
    0.22
    *******č↵
    0.22
    /operators
    0.22
    orch
    0.21
    ftype
    0.21
    *****č↵
    0.21
    '].$
    0.20
    ******č↵
    0.20
    etter
    0.20
    aeda
    0.19
    Activations Density 0.010%

    No Known Activations