© 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. 32184
    Prev
    Next
    INDEX
    Explanations

    dollar amounts, area, duration

    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
    oghi
    -0.08
    alum
    -0.08
    CDATA
    -0.08
     billions
    -0.08
    亿人
    -0.08
    /favicon
    -0.08
    osting
    -0.08
    icus
    -0.08
    æ±ĤçĶŁ
    -0.07
    |max
    -0.07
    POSITIVE LOGITS
    å·¦åı³çļĦ
    0.08
    à¹Ģศษ
    0.07
    خر
    0.07
    eters
    0.07
     ÙĪÙĨصÙģ
    0.07
    å·¦åı³
    0.07
    ith
    0.07
     [
    0.06
    æľīä½Ļ
    0.06
    ha
    0.06
    Activations Density 0.284%

    No Known Activations