© 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. 23014
    Prev
    Next
    INDEX
    Explanations

    numbers, elements, powers, index

    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
    ®,
    -0.07
    äºĶ常
    -0.06
    人æĦı
    -0.06
     обоз
    -0.06
    avi
    -0.06
    æ±Ĥ人
    -0.06
    اØŃ
    -0.06
    ä»ij
    -0.06
    ~/
    -0.06
    unset
    -0.06
    POSITIVE LOGITS
    iores
    0.08
    ä¹ĥèĩ³
    0.07
    unar
    0.07
    /non
    0.07
    æĪĸéĿŀ
    0.07
     dentre
    0.07
    udas
    0.07
     parmi
    0.07
     olmayan
    0.07
    ÙħÛĮÙĨ
    0.07
    Activations Density 0.052%

    No Known Activations