© 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. 977
    Prev
    Next
    INDEX
    Explanations

    concealing or hiding something

    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
    å©¿
    -0.07
    hund
    -0.07
    ointed
    -0.07
    izer
    -0.07
    تÙĪÙĨ
    -0.07
    åħ¨ä½ĵ人åijĺ
    -0.07
    antic
    -0.07
    çļĦ人äºĨ
    -0.07
    aven
    -0.07
    ldr
    -0.07
    POSITIVE LOGITS
    éļIJèĹı
    0.10
    èĹıçĿĢ
    0.10
     hides
    0.10
    èĶ½
    0.10
    -hidden
    0.09
    踪迹
    0.09
    ä¸įä½ıçļĦ
    0.09
    éļł
    0.09
     hiding
    0.09
    æİĸ
    0.09
    Activations Density 0.057%

    No Known Activations