© 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. 17056
    Prev
    Next
    INDEX
    Explanations

    regardingconcerningapparentable

    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
    ramids
    -0.08
    ież
    -0.08
    åĴĮ社ä¼ļä¿Ŀéļľ
    -0.07
    è¾Ĩ
    -0.07
    ï¸ı
    -0.07
    رس
    -0.07
    DIRECTORY
    -0.07
    ä¸įå¾ĹäºĨ
    -0.07
    /her
    -0.07
    elves
    -0.07
    POSITIVE LOGITS
    able
    0.10
     regarding
    0.10
    åħ³äºİ
    0.09
    inent
    0.09
    abled
    0.08
    ested
    0.07
     Regarding
    0.07
    actical
    0.07
     concerning
    0.07
     apparent
    0.06
    Activations Density 0.730%

    No Known Activations