© 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. 58158
    Prev
    Next
    INDEX
    Explanations

    constitutional amendment

    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
    صر
    -0.08
    èł»
    -0.08
    æ²¹æ¼Ĩ
    -0.08
    å½¢èī²
    -0.08
    çļĦä¸Ģ线
    -0.08
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.08
    á»ĵi
    -0.07
    munition
    -0.07
    avin
    -0.07
     sofist
    -0.07
    POSITIVE LOGITS
    宪æ³ķ
    0.12
     constitutional
    0.10
     Constitutional
    0.10
    constitutional
    0.09
     unconstitutional
    0.09
     ÐļонÑģÑĤиÑĤÑĥ
    0.08
    æĨ²
    0.08
     constitution
    0.08
    宪
    0.08
    ä¿¡ä»°
    0.08
    Activations Density 0.010%

    No Known Activations