© 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. 27137
    Prev
    Next
    INDEX
    Explanations

    economic rates and unemployment

    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
     плоÑīадÑĮÑİ
    -0.07
    ross
    -0.07
    壯
    -0.07
    åĴĮçī¹çĤ¹
    -0.07
    Ỽp
    -0.06
    åıĮ缮
    -0.06
    маÑģ
    -0.06
     Mach
    -0.06
    ÑīоÑĤо
    -0.06
    æĸ¹çļĦçºłçº·
    -0.06
    POSITIVE LOGITS
    jug
    0.09
    geld
    0.07
    veille
    0.07
    hawk
    0.07
    åŁºåĩĨåĪ©çİĩ
    0.07
    为æ°ij
    0.07
     pled
    0.07
    ä¼łå¯¼
    0.07
     gover
    0.07
    èģ´
    0.07
    Activations Density 0.016%

    No Known Activations