© 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. 60911
    Prev
    Next
    INDEX
    Explanations

    conditional expressions `if`, `ifeq`, `ifneq`, `$(if`

    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
    éķ¿æĮīè¯ĨåĪ«
    -0.06
     fitness
    -0.06
    çłĶ究人åijĺ
    -0.06
     //</
    -0.06
    æĬĬä¸Ģ个
    -0.06
     getters
    -0.06
     fixture
    -0.06
    umat
    -0.06
    empel
    -0.06
    empo
    -0.06
    POSITIVE LOGITS
    bling
    0.08
    å¾·åŁº
    0.08
    οÏįÏĤ
    0.08
    arguments
    0.08
     GMO
    0.08
    skyl
    0.08
    _spacing
    0.08
    é»İæĺİ
    0.07
    åĪ¶å®ļæľ¬
    0.07
    辯
    0.07
    Activations Density 0.231%

    No Known Activations