© 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. 50811
    Prev
    Next
    INDEX
    Explanations

    transparency and transparency

    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
    人çĶŁä¸Ń
    -0.08
    å¨ĩ
    -0.08
    WithError
    -0.07
    dle
    -0.07
    Ordinal
    -0.07
    æĭ¬
    -0.07
    oted
    -0.07
    AtPath
    -0.07
    ä½ĵä¼ļ
    -0.07
    çĤ¹æѤ
    -0.07
    POSITIVE LOGITS
     transparency
    0.19
    éĢıæĺİ
    0.18
    éĢıæĺİ度
    0.18
     transparent
    0.16
    éĢıæĺİçļĦ
    0.16
     Transparency
    0.16
     Transparent
    0.14
     пÑĢозÑĢа
    0.14
     transpare
    0.14
    ä¿¡æģ¯åħ¬å¼Ģ
    0.13
    Activations Density 0.086%

    No Known Activations