© 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. 45472
    Prev
    Next
    INDEX
    Explanations

    who or people

    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
    åľ¨èº«
    -0.08
    ert
    -0.08
     itself
    -0.08
    æĪĺ士们
    -0.07
    éĥ¨åĪĨåĨħ容
    -0.07
    è§Ĥä¼Ĺ们
    -0.07
    erta
    -0.07
    erte
    -0.07
    annies
    -0.07
    ä¸Ģå¹ķ
    -0.06
    POSITIVE LOGITS
     who
    0.12
     else
    0.10
    who
    0.09
    /people
    0.09
     whom
    0.09
    誰ãģ§ãĤĤ
    0.09
    /team
    0.09
    /groups
    0.09
    è°ģ
    0.09
     kto
    0.09
    Activations Density 0.437%

    No Known Activations