© 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. 17057
    Prev
    Next
    INDEX
    Explanations

    tailored new breed

    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
    Ķ
    -0.07
    IFE
    -0.06
    CF
    -0.06
     impro
    -0.06
    ubb
    -0.06
     Pretty
    -0.06
     AFC
    -0.06
    æīĭä¸Ĭ
    -0.06
     spread
    -0.06
    âĢ¦”
    -0.06
    POSITIVE LOGITS
     Saud
    0.08
    åij³åĦ¿
    0.08
    /licenses
    0.07
    åħ¶æŀĹ
    0.07
     osta
    0.07
    ittle
    0.07
    iets
    0.07
    ä¸Ĭèħº
    0.07
    ACHER
    0.07
    odial
    0.07
    Activations Density 0.038%

    No Known Activations