© 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. 48584
    Prev
    Next
    INDEX
    Explanations

    economy and finance expenditures

    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
    ICON
    -0.08
    å±±ä¹ĭ
    -0.07
    WISE
    -0.07
    acon
    -0.07
    ksam
    -0.06
    vie
    -0.06
    é£İ头
    -0.06
    BSD
    -0.06
    sea
    -0.06
    æĤį
    -0.06
    POSITIVE LOGITS
    _constants
    0.08
    _SCR
    0.08
    Multiplier
    0.08
     totals
    0.07
    Idle
    0.07
    ikian
    0.07
    stad
    0.07
    èĩªåıij
    0.07
    setMax
    0.07
     basics
    0.07
    Activations Density 0.001%

    No Known Activations