© 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. 20305
    Prev
    Next
    INDEX
    Explanations

    counts, types, nations, colors

    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
    ç»ĵæŀĦè°ĥæķ´
    -0.08
    ehl
    -0.08
    acre
    -0.07
    æĬ¢å¤º
    -0.07
    NDER
    -0.07
    cula
    -0.07
    udi
    -0.07
    绩æķĪè¯Ħä»·
    -0.06
    _tim
    -0.06
    ãĥIJãĥĥ
    -0.06
    POSITIVE LOGITS
     range
    0.08
    èĮĥåĽ´åĨħ使çĶ¨
    0.08
    range
    0.08
     distinct
    0.08
    Subset
    0.08
    å¤ļæł·çļĦ
    0.08
    Range
    0.08
     Range
    0.07
    çļĦèĮĥåĽ´
    0.07
    æµģè¿ŀ
    0.07
    Activations Density 0.022%

    No Known Activations