© 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. 50457
    Prev
    Next
    INDEX
    Explanations

    zapine

    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
    èİŀ
    -0.07
    ç«ĭä½ĵ
    -0.07
    è´¢æĶ¿æĶ¶åħ¥
    -0.06
     Erl
    -0.06
    rane
    -0.06
    éij
    -0.06
    家åºŃçĶŁæ´»
    -0.06
    indra
    -0.06
    æ¶Īè´¹
    -0.06
    ikat
    -0.06
    POSITIVE LOGITS
     tester
    0.10
    esting
    0.08
    TypeInfo
    0.08
     Mercy
    0.08
    软件æµĭè¯ķ
    0.08
     testen
    0.08
     Testing
    0.08
     tests
    0.08
    youtu
    0.08
     testers
    0.08
    Activations Density 0.001%

    No Known Activations