© 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. 120
    Prev
    Next
    INDEX
    Explanations

    instructional text examples

    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
     Según
    -0.28
     }};↵
    -0.28
    æĢ»èĢĮè¨Ģ
    -0.27
    urances
    -0.25
    (*)(
    -0.25
    確ãģĭãģ«
    -0.23
     ãĥĪãĥ©ãĥĥãĤ¯
    -0.23
    ä»İ严治
    -0.22
    .Disclaimer
    -0.22
    iferay
    -0.21
    POSITIVE LOGITS
     example
    0.35
     if
    0.35
     note
    0.34
     If
    0.32
     this
    0.32
     Note
    0.32
     only
    0.30
    èĭ¥
    0.30
     Example
    0.28
    å¦Ĥæŀľ
    0.28
    Activations Density 2.386%

    No Known Activations