© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 27651
    Prev
    Next
    INDEX
    Explanations

    biological cycles and stages

    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
    æĶĢæ¯Ķ
    -0.07
    äºĮå±Ĥ
    -0.06
    reds
    -0.06
    ÙİعÙĴ
    -0.06
    缴æİ¥
    -0.06
    åīįæİĴ
    -0.06
    raid
    -0.06
    äºĮä½į
    -0.06
    第äºĮ代
    -0.06
    undial
    -0.06
    POSITIVE LOGITS
    å§ĭäºİ
    0.10
     nutshell
    0.09
     stages
    0.08
    ä¾Ŀ次为
    0.08
    —from
    0.08
     steps
    0.08
     stappen
    0.08
    ä¾Ŀ次
    0.08
     cycle
    0.07
    å§ĭèĩ³
    0.07
    Activations Density 0.186%

    No Known Activations