© 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. 2504
    Prev
    Next
    INDEX
    Explanations

    measurements and quantities

    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
     minus
    -0.22
    讹
    -0.21
    warz
    -0.20
    åĬŀ好
    -0.20
     ---------------------------------------------------------------------------↵
    -0.19
    ople
    -0.19
    ä¹°ä¸ľè¥¿
    -0.19
    weak
    -0.19
    æĺ³
    -0.18
    ousse
    -0.18
    POSITIVE LOGITS
    -tm
    0.25
     addCriterion
    0.23
    Į¨
    0.21
    <fieldset
    0.21
    )))),
    0.20
    âļĹ
    0.19
     }}"><
    0.19
    å©¿
    0.19
    polator
    0.19
    ooke
    0.19
    Activations Density 0.158%

    No Known Activations