© 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. 30622
    Prev
    Next
    INDEX
    Explanations

    is followed by a noun phrase

    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
    举ä¸Ģåıįä¸ī
    -0.07
    åĮĸå¤ĦçIJĨ
    -0.07
    Lite
    -0.06
    ipes
    -0.06
    å°½æľī
    -0.06
    niki
    -0.06
    åĴĮä¸Ģ
    -0.06
    éħĴå±ĭ
    -0.06
    _SUFFIX
    -0.06
     âĤ¬,
    -0.06
    POSITIVE LOGITS
    schlag
    0.07
    uage
    0.07
    aped
    0.07
     Thrones
    0.07
    erb
    0.06
    uet
    0.06
    èªķ
    0.06
    adhan
    0.06
    è¯ŀ
    0.06
    udian
    0.06
    Activations Density 1.158%

    No Known Activations