© 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. 61718
    Prev
    Next
    INDEX
    Explanations

    events and gatherings

    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
    esame
    -0.08
    .setdefault
    -0.08
    gart
    -0.08
    //{{
    -0.08
    PROP
    -0.08
    æĶ¹éĢł
    -0.08
    éĥ½ä¸įçĶ¨
    -0.08
    ->{
    -0.08
    éĻ¤æģ¶
    -0.08
    ä¸Ģ个åı«
    -0.08
    POSITIVE LOGITS
     celebrating
    0.06
     hosted
    0.06
     probing
    0.06
     veranst
    0.06
    åłĤ
    0.06
    -modules
    0.06
     vision
    0.06
    :
    0.06
    é«ĺ涨
    0.06
     visionary
    0.05
    Activations Density 0.109%

    No Known Activations