© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14990
    Prev
    Next
    INDEX
    Explanations

    .set, url, and frequency assignments

    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
    mien
    -0.09
    Õ¸Õ²
    -0.08
    çıĬçıĬ
    -0.08
    opodob
    -0.08
    æĭĽåķĨ
    -0.08
    à¹Ģà¸ģร
    -0.08
    Õ¡Õ¿
    -0.08
    abox
    -0.08
     pales
    -0.08
    춤
    -0.08
    POSITIVE LOGITS
     automatic
    0.07
     sin
    0.06
     c
    0.06
     aut
    0.06
     max
    0.06
    æŃ»
    0.06
     “
    0.06
    omp
    0.05
     configFile
    0.05
    çİ°æľīçļĦ
    0.05
    Activations Density 0.575%

    No Known Activations