© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25797
    Prev
    Next
    INDEX
    Explanations

    nlohmann or glm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    actory
    -0.07
    esson
    -0.07
    edList
    -0.07
    leman
    -0.07
    æĥĬéŃĤ
    -0.07
     Conserv
    -0.07
    Õ¡Õ£
    -0.06
    æĢĢ
    -0.06
    èĬĤå¥ı
    -0.06
     Nai
    -0.06
    POSITIVE LOGITS
    uhu
    0.08
    chg
    0.07
    orius
    0.07
    jena
    0.07
    ysl
    0.07
    æģ°åĪ°
    0.07
    ulos
    0.07
    opa
    0.07
    allas
    0.07
    etos
    0.07
    Activations Density 0.012%

    No Known Activations