© 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. 23298
    Prev
    Next
    INDEX
    Explanations

    differential forms or Omega notation

    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
    èĩ¼
    -0.07
    apar
    -0.06
    æ²³ä¸Ń
    -0.06
     merit
    -0.06
    ä¸ĬæľŁ
    -0.06
    ekin
    -0.06
    æĬ±
    -0.06
     Cement
    -0.06
    è¿Ļæī¹
    -0.06
    嫦娥
    -0.06
    POSITIVE LOGITS
    onale
    0.09
    æ»´æ»´
    0.08
     everywhere
    0.08
    éĿ©
    0.08
    letic
    0.08
    è¾ħ
    0.08
    äºĮ度
    0.07
    æ²Ļæ²Ļ
    0.07
    声
    0.07
    icch
    0.07
    Activations Density 0.011%

    No Known Activations