© 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. 51130
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code

    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
    缮ä¸Ń
    -0.08
    èµ°ä¸Ģèµ°
    -0.08
    åIJİèĩ³
    -0.08
    éĩįæĿ¥
    -0.07
    _PRIORITY
    -0.07
    RIORITY
    -0.07
    ä¸ĢæĿ¡é¾Ļ
    -0.07
    ÙĥÙIJ
    -0.07
    å¹¶è¿Ľ
    -0.07
    SETTING
    -0.07
    POSITIVE LOGITS
    æĮ¨
    0.07
    绵
    0.07
    毫ä¸į
    0.06
    çĹħ
    0.06
    森
    0.06
    ué
    0.06
     umb
    0.06
    aven
    0.06
    æ²»
    0.06
    aul
    0.06
    Activations Density 0.010%

    No Known Activations