© 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. 45380
    Prev
    Next
    INDEX
    Explanations

    numbers and exponents

    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
    incinn
    -0.07
    ullo
    -0.06
    ·
    -0.06
    ãĢĪ
    -0.06
     tru
    -0.06
    Subset
    -0.06
    以ä¸Ĭ
    -0.05
    å¼Ģ好
    -0.05
    æĮĩ
    -0.05
    lots
    -0.05
    POSITIVE LOGITS
    ilog
    0.09
    å¢ĥçļĦ
    0.09
    ľ
    0.08
    èİ«åıĬ
    0.08
    isel
    0.08
    åħ°çī¹
    0.08
    קר
    0.08
    åĽŀçŃĶéĩı
    0.08
     gesta
    0.08
    arged
    0.08
    Activations Density 0.002%

    No Known Activations