© 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. 1861
    Prev
    Next
    INDEX
    Explanations

    structured text fragments

    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
    Jeste
    -0.23
    å¾Īå¤ļçݩ家
    -0.21
     Turns
    -0.20
    쨰
    -0.19
    umed
    -0.19
     Rather
    -0.18
    ÑĦикÑģ
    -0.18
    Rather
    -0.18
    â½ī
    -0.18
    .scalablytyped
    -0.18
    POSITIVE LOGITS
    游æĪıæĬĢå·§
    0.25
    åĹIJ
    0.24
    纰
    0.23
    -License
    0.22
    HandlerContext
    0.22
    geist
    0.21
    SizePolicy
    0.21
    -bedroom
    0.21
    åķµ
    0.20
    èĩ³æĸ¼
    0.20
    Activations Density 0.493%

    No Known Activations