© 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. 16128
    Prev
    Next
    INDEX
    Explanations

    Calendar events

    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
    ]+\
    -0.08
    .Reader
    -0.07
    +"]
    -0.07
    stä
    -0.07
    ijľ
    -0.07
    =>
    -0.07
    }while
    -0.07
    à¸Ĺัà¹īà¸ĩสิà¹īà¸Ļ
    -0.07
    ]->
    -0.07
    éĻ¤å¤ĸ
    -0.07
    POSITIVE LOGITS
    isson
    0.08
    eros
    0.07
    âĢİ
    0.07
    κολοÏħ
    0.07
    æĪĪå°Ķ
    0.07
     isEqual
    0.06
    errat
    0.06
    äºĨ解åĴĮ
    0.06
    æ´Ľä¼Ĭ
    0.06
    issons
    0.06
    Activations Density 0.017%

    No Known Activations