© 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. 22112
    Prev
    Next
    INDEX
    Explanations

    days of the week

    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
    å½ĵæŶçļĦ
    -0.09
    å½ĵæŶ
    -0.08
     aforementioned
    -0.07
     damal
    -0.07
     ðŁĺī
    -0.06
    è§ī
    -0.06
     afore
    -0.06
     اÛĮشاÙĨ
    -0.06
    çķ¶æĻĤ
    -0.06
     éve
    -0.06
    POSITIVE LOGITS
    ä¸ĭéĿ¢æĺ¯å°ıç¼ĸ
    0.08
    åĨįæ·»
    0.08
    æľ¬åij¨
    0.08
    è¿ijæĹ¥
    0.08
     Stor
    0.07
    arcz
    0.07
    æŶä¸ĭ
    0.07
    æŶéļĶ
    0.07
    à¸ģราà¸Ļ
    0.07
     Globe
    0.07
    Activations Density 3.858%

    No Known Activations