© 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. 15690
    Prev
    Next
    INDEX
    Explanations

    human body parts and fluids

    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
    ngthen
    -0.08
     grano
    -0.08
     Independ
    -0.08
    лай
    -0.08
    å°¼äºŀ
    -0.08
    åĵģç§įçļĦ
    -0.08
    roda
    -0.08
    ['__
    -0.07
    æĢ§åŃIJ
    -0.07
    西äºŀ
    -0.07
    POSITIVE LOGITS
    æĺ¯äººä½ĵ
    0.14
    人ä½ĵ
    0.11
     humain
    0.10
     humano
    0.10
     human
    0.10
     umano
    0.10
     humana
    0.10
    人ä½ĵçļĦ
    0.09
     humanas
    0.09
    æĺ¯äºº
    0.09
    Activations Density 0.264%

    No Known Activations