© 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. 240
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
    ederland
    -0.21
    auce
    -0.19
    ãĤĴéĽĨãĤģ
    -0.18
    éĶī
    -0.18
    obierno
    -0.18
    	fflush
    -0.18
    èĨĪ
    -0.17
    loquent
    -0.17
    vil
    -0.17
    ouis
    -0.17
    POSITIVE LOGITS
    (x
    0.25
     FactoryBot
    0.24
    matchCondition
    0.23
    FunctionFlags
    0.22
    ãĥµ
    0.21
     UnityEditor
    0.21
    å¹´ä¹ĭ
    0.21
     TMPro
    0.21
     HeaderComponent
    0.20
    ìĬ¹
    0.19
    Activations Density 0.231%

    No Known Activations