© 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. 8788
    Prev
    Next
    INDEX
    Explanations

    exoplanet and transit observations

    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
    åĪĨåĮº
    -0.07
    sons
    -0.07
    å°ĶåŁº
    -0.07
    å±Ģéĥ¨
    -0.06
    æĸ°çĶŁçļĦ
    -0.06
     bunk
    -0.06
     distrib
    -0.06
    æľĢé«ĺ
    -0.06
     defaultMessage
    -0.06
    æŧçļĦ
    -0.06
    POSITIVE LOGITS
     detections
    0.09
    монÑĤ
    0.09
    èĴĻçī¹
    0.09
    读åĩº
    0.08
     detection
    0.08
    ensing
    0.08
    Cla
    0.08
    æĻķ
    0.08
    éķ¿çĽ¸
    0.08
    detect
    0.08
    Activations Density 0.022%

    No Known Activations