© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 52160
    Prev
    Next
    INDEX
    Explanations

    digital converters and systems

    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
    Negative Logits
    ÙĨÙģ
    -0.09
     attrib
    -0.07
    lan
    -0.07
    çĥŃåĬĽ
    -0.07
    éĶĻ综
    -0.07
     supporter
    -0.07
    visibility
    -0.07
    ล
    -0.07
    .createServer
    -0.07
     Molina
    -0.07
    POSITIVE LOGITS
    digital
    0.08
     digital
    0.08
     Digital
    0.08
    decimal
    0.08
     sampling
    0.08
    sampling
    0.08
     Sampling
    0.08
     decimal
    0.08
    ä½įæķ°
    0.07
    fehler
    0.07
    Activations Density 0.042%

    No Known Activations