© 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. 51623
    Prev
    Next
    INDEX
    Explanations

    judgmental terms

    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
    quire
    -0.08
    åĴĮæĢĿèĢĥ
    -0.07
    egu
    -0.07
    èĬĤåĪ¶
    -0.07
    latin
    -0.07
    被认为
    -0.07
    erber
    -0.07
    被认为æĺ¯
    -0.07
    大æĪ·
    -0.06
    allery
    -0.06
    POSITIVE LOGITS
     ÙĪØ£ÙĨÙĩ
    0.11
     بÙĪدÙĨ
    0.10
    acy
    0.09
    è·Łä»ĸ们
    0.07
    祺
    0.07
    åĴĮèĩªå·±
    0.07
    è¿Īåĩº
    0.07
    using
    0.07
    afe
    0.07
    信念
    0.07
    Activations Density 0.172%

    No Known Activations