© 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. 369
    Prev
    Next
    INDEX
    Explanations

    biological/technical terms

    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
    NavController
    -0.23
    央ä¼ģ
    -0.22
    (nonatomic
    -0.20
    æĭĽèģĺä¿¡æģ¯
    -0.19
    ãĢĤãĢĤ↵↵
    -0.19
     ``
    -0.19
    BootTest
    -0.19
    bindParam
    -0.19
    PickerController
    -0.19
    æĹłå¿§
    -0.18
    POSITIVE LOGITS
    ç®Ģ称
    0.33
    .epam
    0.28
    ;;;;;;;;
    0.27
     ());↵↵
    0.24
    [Boolean
    0.23
    "';
    0.23
    ["$
    0.23
    以ä¸ĭç®Ģ称
    0.22
    (){}↵↵
    0.22
    ;base
    0.21
    Activations Density 5.352%

    No Known Activations