© 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. 10419
    Prev
    Next
    INDEX
    Explanations

    legal rulings and outcomes

    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
    endl
    -0.07
     prens
    -0.07
    常åĬ¡çIJĨäºĭ
    -0.07
    ÙĬاء
    -0.06
    æĺĵ
    -0.06
     Cliff
    -0.06
    æĹ¥çĶŁ
    -0.06
    location
    -0.06
    è£ħ
    -0.06
    è½
    -0.06
    POSITIVE LOGITS
    uario
    0.09
    aled
    0.09
    并å®ĮæĪIJ
    0.08
     administr
    0.08
    å®ŀä½ĵ
    0.07
    çĶŁæķĪä¹ĭæĹ¥èµ·
    0.07
    aland
    0.07
    å¯¹çĽ¸åħ³
    0.07
     duly
    0.07
     successful
    0.07
    Activations Density 0.068%

    No Known Activations