© 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. 30471
    Prev
    Next
    INDEX
    Explanations

    mathematical terms or units

    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
    æ²»
    -0.08
    iat
    -0.06
    oe
    -0.06
     means
    -0.06
    æĭ¬
    -0.06
    念
    -0.06
    esh
    -0.06
    Zen
    -0.06
    O
    -0.06
    æ·»
    -0.06
    POSITIVE LOGITS
    ä¸įå°ijçļĦ
    0.09
     Leverkus
    0.08
    åĨįæİ¥
    0.08
    ytter
    0.08
    ÙĪØ·
    0.08
     recal
    0.08
    zyw
    0.08
    ีà¹Īยว
    0.08
    .compute
    0.07
    大éªĤ
    0.07
    Activations Density 0.002%

    No Known Activations