© 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. 62152
    Prev
    Next
    INDEX
    Explanations

    Karlsruhe High

    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
    çıŃä¸Ĭ
    -0.08
     ØŃاÙĦÛĮ
    -0.08
    URT
    -0.07
    æ·±åħ¥åŃ¦ä¹łè´¯å½»
    -0.07
    ONTAL
    -0.07
    áŀ»áŀĦ
    -0.07
    ä½ľåĵģåĨħ容
    -0.07
    emper
    -0.07
    jana
    -0.07
    vidence
    -0.07
    POSITIVE LOGITS
    å¤Ħ女
    0.08
    енÑĤ
    0.07
    ãĤĮãģŁãĤĬ
    0.06
    igas
    0.06
    ä½įç½®åĴĮ
    0.06
    åľ°ä½įåĴĮ
    0.06
     indebted
    0.06
     commonplace
    0.06
     ‘
    0.06
    è¿Ļåı¯èĥ½æĺ¯
    0.05
    Activations Density 0.486%

    No Known Activations