© 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. 8564
    Prev
    Next
    INDEX
    Explanations

    example * A if NOT

    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
    ë§ĪìŀIJ
    -0.09
     (!((
    -0.09
    warzys
    -0.08
    Ù°
    -0.08
    们éĥ½
    -0.08
    ики
    -0.08
    opyright
    -0.07
    aser
    -0.07
    اÙĭ
    -0.07
    ../
    -0.07
    POSITIVE LOGITS
    ed
    0.09
    inition
    0.09
    ÏĤ
    0.09
    ê°ĢëĬĶ
    0.09
    kler
    0.08
    elly
    0.08
    åľ¨
    0.08
    edel
    0.08
    s
    0.08
    ات
    0.08
    Activations Density 0.101%

    No Known Activations