© 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. 29069
    Prev
    Next
    INDEX
    Explanations

    individuals or groups

    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
    åħ¶ä»ĸ人çļĦ
    -0.10
    jang
    -0.10
    ä¼´ä½ł
    -0.09
    è´Łè´£äººçļĦ
    -0.08
    对æīĭçļĦ
    -0.08
     Teachers
    -0.08
    让åIJĮåѦ们
    -0.08
    èĢģå¸Ī们
    -0.08
    å°ıåŃ©çļĦ
    -0.08
    主人çļĦ
    -0.08
    POSITIVE LOGITS
     consenting
    0.09
    ä¹İåħ¶
    0.08
     eligible
    0.08
     reluctant
    0.08
     individuals
    0.08
    individual
    0.08
     susceptible
    0.07
    符åIJĪæĿ¡ä»¶çļĦ
    0.07
     deserving
    0.07
     young
    0.07
    Activations Density 1.835%

    No Known Activations