© 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. 20678
    Prev
    Next
    INDEX
    Explanations

    regulation and restriction

    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
    æ²Ł
    -0.08
    ä¸įæī¿æĭħä»»ä½ķ
    -0.07
    wab
    -0.06
    erness
    -0.06
    nö
    -0.06
    ä¸įè¾ľè´Ł
    -0.06
    é¢Ħç¥Ŀ
    -0.06
    hq
    -0.06
    èıĮ群
    -0.06
    åIJijãģį
    -0.06
    POSITIVE LOGITS
    éĻIJåĪ¶
    0.13
     restrictions
    0.12
     restrict
    0.12
    éĻIJ
    0.12
    强åĪ¶
    0.12
     restricting
    0.11
    restrict
    0.11
     restrictive
    0.11
    è§Ħå®ļ
    0.11
     enforced
    0.11
    Activations Density 0.243%

    No Known Activations