© 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. 14836
    Prev
    Next
    INDEX
    Explanations

    analyze something

    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
    à¹Īาย
    -0.08
    ãĤĴæŀľãģŁ
    -0.07
    érance
    -0.07
     absoluta
    -0.07
    nern
    -0.07
    wald
    -0.07
    ington
    -0.07
    มั
    -0.07
    ë²Ħ
    -0.07
    Ãłnh
    -0.07
    POSITIVE LOGITS
    åĴĮåĪĨæŀIJ
    0.10
    åĪĨæŀIJ
    0.09
    éĢıå½»
    0.09
     mendalam
    0.09
     ë¶ĦìĦĿ
    0.09
    alyze
    0.09
    Analy
    0.09
     analyze
    0.08
    วิà¹Ģà¸Ħราะหà¹Į
    0.08
     анализ
    0.08
    Activations Density 0.105%

    No Known Activations