© 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. 17364
    Prev
    Next
    INDEX
    Explanations

    rebel fleet, C++ console, .com, .js

    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
    zan
    -0.08
    zec
    -0.08
    aire
    -0.07
    ä¸¤åĽ½
    -0.07
    anon
    -0.06
    uvan
    -0.06
    vt
    -0.06
    RA
    -0.06
    opot
    -0.06
    çĪ¬ä¸Ĭ
    -0.06
    POSITIVE LOGITS
    让å°ı
    0.08
     Ø´ÙĪر
    0.07
    èĩªå·±åİ»
    0.07
     Chal
    0.07
    utura
    0.07
    EME
    0.07
    ä»İå°ı
    0.07
    éĢ¼
    0.07
    ajem
    0.07
    ahas
    0.07
    Activations Density 0.705%

    No Known Activations