© 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. 16835
    Prev
    Next
    INDEX
    Explanations

    age or point in time

    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
    åĮºåĪ«äºİ
    -0.08
    级以ä¸Ĭ
    -0.08
    éĩijæĸ¯
    -0.08
    诸å¦Ĥ
    -0.08
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    -0.07
    нибÑĥдÑĮ
    -0.07
     *_
    -0.07
    ä¹ĭæīĢ以
    -0.07
    å¦ĤåĽł
    -0.07
    iev
    -0.07
    POSITIVE LOGITS
     (-
    0.07
    angler
    0.07
    éĪį
    0.06
    ä»»
    0.06
     specifier
    0.06
    ãĥ¼ãĥĪãĥ«
    0.06
     flush
    0.06
    çķ¥
    0.06
     mö
    0.06
    oran
    0.06
    Activations Density 0.026%

    No Known Activations