© 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. 2972
    Prev
    Next
    INDEX
    Explanations

    petrol and longitude coordinates

    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
    åIJĮæĹ¶ä¹Łè¦ģ
    -0.07
    icii
    -0.07
    éĿĻ
    -0.07
    é¦ĸåħĪéľĢè¦ģ
    -0.07
    é¦ĸåħĪè¦ģ
    -0.06
    è¾Ł
    -0.06
    LOT
    -0.06
    å¸Ĩ
    -0.06
    ogl
    -0.06
    åĩ¡
    -0.06
    POSITIVE LOGITS
    ä»İèĢĮ导èĩ´
    0.08
    åľ¨æŃ¤åŁºç¡Ģä¸Ĭ
    0.08
     emin
    0.07
    饪
    0.07
    åĢĴäºĨ
    0.07
    IKE
    0.07
     Mancha
    0.07
     Sehingga
    0.07
     therefore
    0.07
    ãĤ³ãĥ³ãĤ»
    0.07
    Activations Density 0.019%

    No Known Activations