© 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. 42397
    Prev
    Next
    INDEX
    Explanations

    modern context

    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
    lesh
    -0.09
    годно
    -0.08
    以赴
    -0.08
    ChangeEvent
    -0.08
    åĴĮçĶ°
    -0.08
    duino
    -0.08
    åı¥è¯Ŀ说
    -0.08
     filmer
    -0.07
    -percent
    -0.07
    adoo
    -0.07
    POSITIVE LOGITS
    ized
    0.12
    -day
    0.11
    ization
    0.11
    ly
    0.11
     اÙĦعÙĩد
    0.10
    izing
    0.10
    -era
    0.10
    ize
    0.09
    -looking
    0.09
    ised
    0.09
    Activations Density 0.022%

    No Known Activations