© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42260
    Prev
    Next
    INDEX
    Explanations

    answer is

    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
    éĥ½æľīäºĨ
    -0.08
     gerek
    -0.07
    ม
    -0.07
    åĿĩå·²
    -0.07
    笼
    -0.07
    onse
    -0.07
    onné
    -0.07
     whatever
    -0.07
    éch
    -0.07
    åħĦ
    -0.07
    POSITIVE LOGITS
    åºĶæĮī
    0.08
    åºĶå½ĵåIJij
    0.08
     should
    0.08
    åºĶæĮīçħ§
    0.07
    enthal
    0.07
    åºĶå½ĵæĮīçħ§
    0.07
    æĶ¶äºĨ
    0.07
    should
    0.07
     most
    0.07
     иной
    0.07
    Activations Density 0.002%

    No Known Activations