© 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. 43849
    Prev
    Next
    INDEX
    Explanations

    state property or officials

    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
    thest
    -0.10
    icult
    -0.08
    iej
    -0.08
    Ùijت
    -0.08
     Æ°á»Ľt
    -0.07
    icultura
    -0.07
    juan
    -0.07
    ụng
    -0.07
    ữa
    -0.07
    ayah
    -0.07
    POSITIVE LOGITS
    -facing
    0.08
    åĴĮ社ä¼ļ
    0.08
    ä½ĵèĤ²æĢ»å±Ģ
    0.08
    åĴĮåĽ½å®¶
    0.08
    å±ĤéĿ¢çļĦ
    0.07
    ëł¹
    0.07
    æĢ§åľ°
    0.07
    åĮĸçļĦ
    0.07
    avern
    0.07
    -sponsored
    0.07
    Activations Density 0.066%

    No Known Activations