© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 47616
    Prev
    Next
    INDEX
    Explanations

    numbers separated by hyphens or 'to'

    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
    us
    -0.07
    ge
    -0.07
    riu
    -0.06
    念头
    -0.06
    _locale
    -0.06
    gez
    -0.06
    “
    -0.06
     matters
    -0.06
    å¯Ŀ
    -0.06
    çı
    -0.06
    POSITIVE LOGITS
     range
    0.10
     Range
    0.10
    range
    0.09
    èĮĥåĽ´
    0.09
     диапазо
    0.09
     ranges
    0.08
    .Range
    0.08
    Range
    0.08
    _RANGE
    0.08
     subrange
    0.08
    Activations Density 0.058%

    No Known Activations