© 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. 41702
    Prev
    Next
    INDEX
    Explanations

    signaling or indicating status

    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
     esque
    -0.08
    اÙħÙĨ
    -0.07
     benchmarks
    -0.07
    urv
    -0.07
    awai
    -0.07
    _again
    -0.07
    ä¸Ģ个ä¸Ģ个
    -0.07
    Benchmark
    -0.07
    -www
    -0.07
    essant
    -0.07
    POSITIVE LOGITS
    以示
    0.12
     indicating
    0.11
    éĨĴ
    0.10
    æłĩè®°
    0.10
    æłĩæĺİ
    0.10
    æ¸ħæ¥ļçļĦ
    0.09
    表æĺİ
    0.09
     unmistak
    0.09
     indication
    0.09
     gekennzeichnet
    0.09
    Activations Density 0.117%

    No Known Activations