© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14756
    Prev
    Next
    INDEX
    Explanations

    moral ethics integrity

    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
    天æīį
    -0.07
    lique
    -0.07
    åĨĹ
    -0.07
    éļĨéļĨ
    -0.07
    ä¸ĢæĻĥ
    -0.07
    elj
    -0.07
    å°±æĢķ
    -0.07
    çļĦç¥ŀå¥ĩ
    -0.07
    å¼Ģèĥĥ
    -0.07
     frustra
    -0.07
    POSITIVE LOGITS
    éģĵå¾·
    0.19
     moral
    0.17
    çļĦéģĵå¾·
    0.17
     morally
    0.15
     morality
    0.15
     Moral
    0.14
     ethical
    0.14
    伦çIJĨ
    0.13
    èģĮä¸ļéģĵå¾·
    0.13
     morals
    0.13
    Activations Density 0.141%

    No Known Activations