© 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. 48280
    Prev
    Next
    INDEX
    Explanations

    incrementing and decrementing 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
    æĢİä¹ĪåĬŀåij¢
    -0.07
    人çĶŁè§Ĥ
    -0.07
    åľ¨å¸Ĥ
    -0.07
    以ä¸ĭåĩłçĤ¹
    -0.07
     semi
    -0.06
    azza
    -0.06
    第äºĮ人æ°ijåĮ»éĻ¢
    -0.06
    онÑĥ
    -0.06
    heads
    -0.06
    骼
    -0.06
    POSITIVE LOGITS
    ustry
    0.08
    ilter
    0.08
    tures
    0.07
    ignet
    0.07
    å·¨æĺŁ
    0.07
    mata
    0.07
    egral
    0.07
    íıŃ
    0.07
    สิà¹īà¸Ļ
    0.07
    ç§Ģ
    0.07
    Activations Density 0.004%

    No Known Activations