© 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. 9834
    Prev
    Next
    INDEX
    Explanations

    hypothalamic region

    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
    没æľī帮åĬ©
    -0.08
    åıijçĶŁåIJİ
    -0.08
    使çĶ¨åīį
    -0.07
    èĮ¬
    -0.07
    baran
    -0.07
     nghĩa
    -0.07
    浪
    -0.07
    åĢº
    -0.06
     pragma
    -0.06
     neger
    -0.06
    POSITIVE LOGITS
    ä¸Ńæŀ¢
    0.10
     centrally
    0.10
     central
    0.09
     centrale
    0.09
    -central
    0.09
    central
    0.09
    ä¸Ń央
    0.08
     pusat
    0.08
    åıĤèĢĥä»·æł¼
    0.08
     ÙħرکزÛĮ
    0.08
    Activations Density 0.086%

    No Known Activations