© 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. 27796
    Prev
    Next
    INDEX
    Explanations

    nanoparticles or elements like Ge, Te, S, N

    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
    ä¸Ģå¾ĭ
    -0.07
    åĴĮ家åºŃ
    -0.07
    åıijçĶŁæŶ
    -0.07
    æīĢæĮĩ
    -0.07
    dle
    -0.06
    åı¯è¨Ģ
    -0.06
    åĴĮæĶ¿æ²»
    -0.06
    æĬµ
    -0.06
    çŃīåIJĦ项
    -0.06
    æľį
    -0.06
    POSITIVE LOGITS
    -dominated
    0.10
    -based
    0.10
    æIJĢ
    0.09
     기ë°ĺ
    0.09
    为主ä½ĵçļĦ
    0.09
    为主çļĦ
    0.08
    alone
    0.08
    based
    0.08
    æĪIJåĬŁåIJİåį³åı¯
    0.08
    åŁºç¤İä¸Ĭ
    0.08
    Activations Density 0.156%

    No Known Activations