© 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. 20712
    Prev
    Next
    INDEX
    Explanations

    mathematical expression 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
    å¤Ħ
    -0.08
    ¾
    -0.07
     λεÏĢ
    -0.07
     Woods
    -0.06
    åijĬ
    -0.06
     sting
    -0.06
    èĥ¡åŃIJ
    -0.06
    äºĭå®ŀä¸Ĭ
    -0.06
    tec
    -0.06
    &R
    -0.06
    POSITIVE LOGITS
    olit
    0.07
    apel
    0.07
    秫
    0.07
    çĭ¬è¡Į
    0.07
    级çļĦ
    0.07
    plib
    0.06
    ?,?,?,?,
    0.06
    ÅŁtir
    0.06
    Coverage
    0.06
    avis
    0.06
    Activations Density 0.017%

    No Known Activations