© 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. 14794
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with 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
    สิà¹īà¸Ļ
    -0.07
    主ä½ĵç»ĵæŀĦ
    -0.07
    ä¹İ
    -0.07
    bergen
    -0.07
    ulon
    -0.07
    ç»ıèIJ¥çĬ¶æĢģ
    -0.07
    ãĥªãĤª
    -0.07
    豪å®ħ
    -0.07
    .strategy
    -0.07
    ropa
    -0.07
    POSITIVE LOGITS
    è¿Ļ两
    0.07
    åħ¨æ°ij
    0.06
    γοÏħ
    0.06
    OfDay
    0.06
     Mancha
    0.06
    èĩªèº«çļĦ
    0.06
    cach
    0.06
    å¹´åīįçļĦ
    0.06
     chảy
    0.06
    人æ°ij
    0.06
    Activations Density 0.011%

    No Known Activations