© 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. 1071
    Prev
    Next
    INDEX
    Explanations

    words related to testing, playing, war, and dimensions

    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
    itesse
    -0.08
     либо
    -0.08
    iett
    -0.08
    baugh
    -0.08
     kuitenkin
    -0.08
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.08
     aforementioned
    -0.07
    ÏĦÎŃÏģ
    -0.07
    zuh
    -0.07
    ache
    -0.07
    POSITIVE LOGITS
    âĢij
    0.10
    âĢIJ
    0.08
     Overview
    0.08
     –
    0.06
    åĶ
    0.06
     “
    0.06
    ²
    0.06
     (“
    0.06
    æī«ä¸Ģæī«
    0.06
    –
    0.06
    Activations Density 0.006%

    No Known Activations