© 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. 30038
    Prev
    Next
    INDEX
    Explanations

    technical terms and products

    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
     bur
    -0.07
    bur
    -0.07
    arna
    -0.07
    	ext
    -0.07
     pl
    -0.06
     Aran
    -0.06
    ons
    -0.06
    éľĢè¦ģæł¹æį®
    -0.06
    çļĦæĥħèĬĤ
    -0.06
    åıĬåħ¶åºĶçĶ¨
    -0.06
    POSITIVE LOGITS
    ancel
    0.08
    éĶ¦æłĩ
    0.07
    actice
    0.07
     or
    0.07
    æĪĸéĥ¨åĪĨ
    0.07
    ETIME
    0.07
    æĪĸ
    0.07
     oder
    0.07
    æĪĸæľª
    0.07
    outing
    0.07
    Activations Density 0.049%

    No Known Activations