© 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. 13263
    Prev
    Next
    INDEX
    Explanations

    Greek letters or mathematical symbols within context

    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
    anford
    -0.09
    reib
    -0.08
    åıijçİ°æľī
    -0.08
    بÙĥ
    -0.08
    rio
    -0.08
    roj
    -0.08
    .selector
    -0.08
    à¸Ĺิà¹īà¸ĩ
    -0.07
    ahari
    -0.07
    LETTE
    -0.07
    POSITIVE LOGITS
    èIJ¨
    0.06
    istring
    0.06
    å°¼å°Ķ
    0.06
     Nada
    0.06
    çĩķ
    0.06
    ä½ıäºĨ
    0.06
    ende
    0.06
    åĶ
    0.06
    दि
    0.06
     indo
    0.06
    Activations Density 0.003%

    No Known Activations