© 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. 26847
    Prev
    Next
    INDEX
    Explanations

    numbers or prices

    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
    å¥Īä½ķ
    -0.07
    urz
    -0.07
     terdekat
    -0.07
    è¿ĩå°ı
    -0.07
    èĢĮçĶŁ
    -0.06
    !“
    -0.06
    åı¯è¨Ģ
    -0.06
    obre
    -0.06
    lia
    -0.06
    ombo
    -0.06
    POSITIVE LOGITS
     oleh
    0.09
     by
    0.09
     вами
    0.08
     bợi
    0.08
     pelos
    0.08
     ÐĴами
    0.08
    çĶ±é«ĺ
    0.08
    Gatt
    0.07
    -Out
    0.07
     мной
    0.07
    Activations Density 0.037%

    No Known Activations