© 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. 48592
    Prev
    Next
    INDEX
    Explanations

    arithmetic operations after variables

    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
    iera
    -0.08
    ray
    -0.07
    æĭ©
    -0.07
    /misc
    -0.07
    éķ¿çŁŃ
    -0.07
    åIJĦåı¸
    -0.07
    æݸ
    -0.07
    iod
    -0.07
    ä¹ħèĢĮ
    -0.06
    å®ļ
    -0.06
    POSITIVE LOGITS
    缸éĤ»
    0.12
     neighboring
    0.10
     neighbouring
    0.10
     adjacent
    0.10
    .next
    0.09
     getNext
    0.09
    éĤ»è¿ij
    0.09
    Adjacent
    0.09
    åīįä¸Ģ
    0.09
     next
    0.09
    Activations Density 0.066%

    No Known Activations