© 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. 7433
    Prev
    Next
    INDEX
    Explanations

    human rights

    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
    Ïĥκο
    -0.08
    ä¸įåı¯æĢķ
    -0.07
    æĸĻçļĦ
    -0.07
    å¤Ħç½ļéĩij
    -0.07
    agini
    -0.07
    åľ¨æīĢ
    -0.07
    çģ«çĥ§
    -0.06
    ź
    -0.06
     strate
    -0.06
    cname
    -0.06
    POSITIVE LOGITS
    ä¿ĿæĬ¤
    0.15
     protections
    0.15
    ä¿Ŀéļľ
    0.15
     protection
    0.14
    ä¿ĿæĬ¤çļĦ
    0.14
     Protect
    0.13
     protecting
    0.13
    人æĿĥ
    0.13
     protects
    0.13
     Protection
    0.13
    Activations Density 0.087%

    No Known Activations