© 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. 12664
    Prev
    Next
    INDEX
    Explanations

    background properties

    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
    gesetz
    -0.07
    è¿ĻäºĽäºĭæĥħ
    -0.07
    ä½Ĩæĺ¯å¥¹
    -0.07
    etz
    -0.07
    tritt
    -0.07
    继èĢĮ
    -0.07
    ä¹īçļĦ
    -0.07
     annak
    -0.06
    HideInInspector
    -0.06
    義
    -0.06
    POSITIVE LOGITS
    å°ĶåŁº
    0.08
     appunto
    0.07
    lest
    0.07
    /antlr
    0.07
    ä¸ĭéĿ¢æĺ¯å°ıç¼ĸ
    0.07
     nonetheless
    0.07
    Æ¡
    0.06
    夷
    0.06
    /welcome
    0.06
    entif
    0.06
    Activations Density 1.078%

    No Known Activations