© 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. 14171
    Prev
    Next
    INDEX
    Explanations

    remembering and mnemonics

    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
    çIJĨ论çłĶ究
    -0.08
    åĮ¿åIJįçĶ¨æĪ·
    -0.07
    è¡Įèĩ³
    -0.07
    æݢ索
    -0.07
    oret
    -0.07
    çIJĨ论ä¸Ĭ
    -0.07
    ter
    -0.06
    undet
    -0.06
     Parr
    -0.06
     blah
    -0.06
    POSITIVE LOGITS
     mnemonic
    0.17
    è®°ä½ı
    0.15
     запом
    0.15
     remembering
    0.14
    è®°ä½ıäºĨ
    0.14
    çī¢è®°
    0.13
    åı£è¯Ģ
    0.13
     memor
    0.13
    è®°å¿Ĩ
    0.13
    è¨ĺä½ı
    0.13
    Activations Density 0.041%

    No Known Activations