© 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. 1551
    Prev
    Next
    INDEX
    Explanations

    time stamps

    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
    女æĺŁ
    -0.23
     Yap
    -0.22
    åİĨåı²æĸ°
    -0.22
    sparse
    -0.21
    íĶĦë¡ľê·¸
    -0.21
    å°ıé¢Ŀ贷款
    -0.21
    plevel
    -0.20
    褡
    -0.20
     esk
    -0.20
    CADE
    -0.20
    POSITIVE LOGITS
    etheless
    0.31
    adays
    0.30
    greSQL
    0.25
    rippling
    0.25
    gether
    0.25
    riger
    0.25
    سبة
    0.24
    -turned
    0.24
    venient
    0.23
    ornment
    0.23
    Activations Density 5.759%

    No Known Activations