© 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. 2511
    Prev
    Next
    INDEX
    Explanations

    support or advocate

    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
    ROTO
    -0.26
    OpenHelper
    -0.26
     IonicPage
    -0.26
    åij¼åĴĮ
    -0.24
    благо
    -0.24
     guarante
    -0.22
     aras
    -0.22
     AssemblyVersion
    -0.21
    ROID
    -0.21
    setattr
    -0.21
    POSITIVE LOGITS
    ä»ģ
    0.26
     idea
    0.25
     against
    0.23
    åĴĮæĶ¯æĮģ
    0.23
    è§ĤçĤ¹
    0.22
    ãĤº
    0.21
    ä¸»å¼ł
    0.21
    /support
    0.21
    æĶ¯æĮģ
    0.21
    çļĦè§ĤçĤ¹
    0.21
    Activations Density 0.380%

    No Known Activations