© 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. 20316
    Prev
    Next
    INDEX
    Explanations

    sys module

    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
    樣çļĦ
    -0.09
    çļĦ人æ°Ķ
    -0.09
    翼翼
    -0.08
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    çļĦå°ıåĮº
    -0.08
    .ping
    -0.08
    级以ä¸Ĭ
    -0.07
    åŁºæľ¬çŁ¥è¯Ĩ
    -0.07
    ahui
    -0.07
    iveness
    -0.07
    POSITIVE LOGITS
    enberg
    0.09
    ®
    0.08
    en
    0.07
    å½ķçĶ¨
    0.07
    blas
    0.07
    imos
    0.07
    ork
    0.07
    vor
    0.07
    åĬĽä½ľ
    0.06
    é¡
    0.06
    Activations Density 0.013%

    No Known Activations