© 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. 21754
    Prev
    Next
    INDEX
    Explanations

    electron/hole pairs

    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
    éĥ¨åĪĨåĨħ容
    -0.07
    istique
    -0.07
    åĮĹè¾°
    -0.07
     Express
    -0.07
    ç¼ĸåĪ¶
    -0.06
    mens
    -0.06
    èµ°åIJijä¸ĸçķĮ
    -0.06
     Aeros
    -0.06
    ìĬµ
    -0.06
    款
    -0.06
    POSITIVE LOGITS
     pairs
    0.08
    å¤ļ空
    0.08
    ç²Ĵ
    0.08
     pair
    0.08
     generated
    0.08
    å¼¥
    0.07
    渡
    0.07
     semiconductor
    0.07
    ucle
    0.07
     liberated
    0.07
    Activations Density 0.022%

    No Known Activations