© 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. 3853
    Prev
    Next
    INDEX
    Explanations

    materials, lighting, batch, form, Erg, plant, pt, volatile, spoil, ological

    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
    éħĿ
    -0.09
    ély
    -0.08
    ÙĪدÛĮ
    -0.08
    asilan
    -0.08
    ูล
    -0.08
     mắm
    -0.08
    notated
    -0.08
    åŁ¼
    -0.08
    abox
    -0.08
    aved
    -0.08
    POSITIVE LOGITS
    åħ¬å¼ĢçļĦ
    0.07
    zet
    0.06
     folk
    0.06
     analog
    0.06
    åħ¬å¼Ģ
    0.06
    thead
    0.06
     gui
    0.06
    ike
    0.06
    ï
    0.06
    instanc
    0.05
    Activations Density 0.192%

    No Known Activations