© 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. 9142
    Prev
    Next
    INDEX
    Explanations

    uniformizing

    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
    wards
    -0.09
    agger
    -0.09
     volna
    -0.08
    !--
    -0.07
    emed
    -0.07
    warzys
    -0.07
     تعاÙĦÙī
    -0.07
    chini
    -0.07
    fulness
    -0.07
    oning
    -0.07
    POSITIVE LOGITS
    ity
    0.14
    ness
    0.11
    ously
    0.10
    ément
    0.10
    ities
    0.09
    -ish
    0.09
    ly
    0.09
    emente
    0.09
    ently
    0.09
    iori
    0.09
    Activations Density 0.013%

    No Known Activations