© 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. 2144
    Prev
    Next
    INDEX
    Explanations

    code/programming

    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
    ',...↵
    -0.23
    asmine
    -0.21
    ä¿¡ä»»
    -0.21
    ĴĮ
    -0.21
    BootApplication
    -0.21
    TÃľ
    -0.21
    cestor
    -0.21
    âĦī
    -0.20
     èĩªåĬ¨çĶŁæĪIJ
    -0.20
    erable
    -0.20
    POSITIVE LOGITS
    elight
    0.21
     '~/
    0.19
     Girlfriend
    0.19
    (substr
    0.19
    .nano
    0.18
    个å¤ļ
    0.18
    lectic
    0.18
    lope
    0.18
    åĽ¹
    0.18
    ä¹ĭä½ľ
    0.18
    Activations Density 0.002%

    No Known Activations