© 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. 13975
    Prev
    Next
    INDEX
    Explanations

    no standard rule or specific marker

    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
    asion
    -0.08
    èĩ³å°ij
    -0.07
     almeno
    -0.07
     mis
    -0.07
    å¿ĥçĶ°
    -0.07
    mis
    -0.07
    Ùİاع
    -0.06
    æľīå¿Ĺ
    -0.06
    acson
    -0.06
    鼶
    -0.06
    POSITIVE LOGITS
    åįķä¸Ģ
    0.11
    åįķä¸ĢçļĦ
    0.11
    绣ä¸ĢçļĦ
    0.10
     definitive
    0.10
     еди
    0.10
    绣ä¸Ģ
    0.09
     tunggal
    0.09
    åĽºå®ļçļĦ
    0.09
    çµ±ä¸Ģ
    0.09
     definit
    0.08
    Activations Density 0.133%

    No Known Activations