© 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. 4390
    Prev
    Next
    INDEX
    Explanations

    simple/solely/purely

    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
    unya
    -0.07
     federally
    -0.06
    hek
    -0.06
    _finished
    -0.06
    é¾Ļä¹ĭ
    -0.06
    å¾Ĺ人
    -0.06
     Brady
    -0.06
    brush
    -0.06
    央
    -0.06
    ano
    -0.06
    POSITIVE LOGITS
     simply
    0.10
     solely
    0.09
    åıªåī©ä¸ĭ
    0.09
     purely
    0.08
     simplemente
    0.08
    åıªéľĢ
    0.08
     semplicemente
    0.08
    åıªéľĢè¦ģ
    0.08
    çĻ½çĻ½
    0.08
     Simply
    0.08
    Activations Density 0.017%

    No Known Activations