© 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. 22225
    Prev
    Next
    INDEX
    Explanations

    informed consent and decision-making

    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
     ÙĦÙĦبÙĨ
    -0.07
    涧
    -0.07
    å¼±
    -0.07
    æŁ¥çľĭçŃĶæ¡Ī解æŀIJ
    -0.07
    ãĤ¸ãĥ³ãĤ°
    -0.07
    头çĸ¼
    -0.06
    ึà¸ĩ
    -0.06
    dden
    -0.06
     punishing
    -0.06
     иÑģпÑĢав
    -0.06
    POSITIVE LOGITS
    çŁ¥æĥħ
    0.10
     informed
    0.09
    /options
    0.09
    宣æķĻ
    0.09
     bedside
    0.09
    æ²ŁéĢļåĴĮ
    0.08
    åĮ»æĤ£
    0.08
    -options
    0.08
    交å¾ħ
    0.08
     Choices
    0.08
    Activations Density 0.212%

    No Known Activations