© 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. 8056
    Prev
    Next
    INDEX
    Explanations

    began its journey

    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
    ellis
    -0.08
    å¾¹
    -0.07
     Polis
    -0.07
    otar
    -0.07
    eko
    -0.07
    ä¸įèĥľ
    -0.06
    arus
    -0.06
    iqu
    -0.06
    çļ®ä¹¦
    -0.06
    åıĮåıĮ
    -0.06
    POSITIVE LOGITS
    å¾IJå¾IJ
    0.08
    _begin
    0.08
    Begin
    0.08
    _extent
    0.08
     begins
    0.07
    ä¼ģä¸ļåıĹçĽĬ
    0.07
    onders
    0.07
     Begin
    0.07
     began
    0.07
    itled
    0.07
    Activations Density 0.061%

    No Known Activations