© 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. 38656
    Prev
    Next
    INDEX
    Explanations

    american politics and culture

    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
    letic
    -0.07
    åĽ½å®¶è§Ħå®ļ
    -0.07
    çıĪ
    -0.07
    leur
    -0.07
     parlament
    -0.07
     Murdoch
    -0.07
    áĥĶáĥłáĥĹ
    -0.07
    Ùħاء
    -0.07
    uggling
    -0.07
    emic
    -0.07
    POSITIVE LOGITS
    æĺ¯ç¾İåĽ½
    0.12
     اÙĦØ£ÙħرÙĬÙĥÙĬØ©
    0.11
    åĬłå·ŀ
    0.10
     Serikat
    0.10
    ç¾İåĽ½çļĦ
    0.10
    æŧéĩijå±±
    0.10
     СШÐIJ
    0.10
    USA
    0.10
    çļĦç¾İåĽ½
    0.10
    ç¾İåĽ½
    0.09
    Activations Density 0.421%

    No Known Activations