© 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. 32203
    Prev
    Next
    INDEX
    Explanations

    in anticipation of / in celebration of

    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
    ç¬ijè¯Ń
    -0.08
    rlen
    -0.08
    ieden
    -0.08
    кÑĢаÑĤно
    -0.08
    anei
    -0.07
    æīĢè°ĵçļĦ
    -0.07
    ì°©
    -0.07
    otka
    -0.07
    两边çļĦ
    -0.07
    ÃģNG
    -0.07
    POSITIVE LOGITS
     inilah
    0.10
     itulah
    0.09
     ìĤ¬ìļ©íķĺë©´
    0.08
    å®ĥå°±ä¼ļ
    0.08
    çļĦä¸Ģå®ļ
    0.07
    çļĦè¿Ļ个
    0.07
    èĢĮè¨Ģ
    0.06
     bowiem
    0.06
    eff
    0.06
     بÙĪدÙĨ
    0.06
    Activations Density 0.632%

    No Known Activations