© 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. 14770
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with numbers

    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
    zik
    -0.09
    erp
    -0.08
    ainer
    -0.08
    aan
    -0.08
     Henn
    -0.08
    pjes
    -0.08
    spel
    -0.08
    缸åĬ©
    -0.08
    erd
    -0.08
    æĽ´å¤ļåħ³äºİ
    -0.08
    POSITIVE LOGITS
    es
    0.07
    s
    0.07
    ://
    0.07
    ÏĤ
    0.07
    æ¯Ľæ³½ä¸ľ
    0.06
    ะ
    0.06
    å°ijå¹´åĦ¿ç«¥
    0.06
     türlü
    0.06
    he
    0.06
    raphic
    0.06
    Activations Density 0.041%

    No Known Activations