© 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. 14096
    Prev
    Next
    INDEX
    Explanations

    if then

    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
    ãĤĤãģĹ
    -0.08
    eki
    -0.07
    _DENIED
    -0.07
     ознаÑĩ
    -0.07
    ison
    -0.07
    éľĢè¦ģäºĨ解
    -0.07
    ä¸ĢåŃĹ
    -0.07
    odie
    -0.07
    ам
    -0.07
    jede
    -0.07
    POSITIVE LOGITS
    å½ĴæĿ¥
    0.07
    æĺ¥æĿ¥
    0.07
    纺
    0.07
    çĤ¹åĩ»ä¸ĭè½½
    0.07
    akk
    0.06
    lage
    0.06
     اÙĦتابع
    0.06
    æŶéļĶ
    0.06
    irim
    0.06
    没äºĭ
    0.06
    Activations Density 0.033%

    No Known Activations