© 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. 46836
    Prev
    Next
    INDEX
    Explanations

    monetary values or physical measurements

    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
    éĽĨåħ¨
    -0.08
    ++++
    -0.07
    cul
    -0.07
    éĽĨçļĦ
    -0.07
     (++
    -0.07
    hd
    -0.06
    æľ¬æĸĩçĶ±
    -0.06
    ampur
    -0.06
    :+
    -0.06
     önem
    -0.06
    POSITIVE LOGITS
    urga
    0.08
    ÏģοÏħ
    0.08
    ائ
    0.08
    æĥ³å¾Ĺ
    0.07
    建åĨĽ
    0.07
    usch
    0.07
    scratch
    0.07
    olim
    0.07
    Ñģев
    0.07
    عر
    0.07
    Activations Density 0.009%

    No Known Activations