© 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. 63584
    Prev
    Next
    INDEX
    Explanations

    rates of decline

    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
    å¾Īä¹ħ
    -0.08
    ResponseBody
    -0.08
    cce
    -0.08
    太ä¹ħ
    -0.08
    nicz
    -0.08
    ÌĢ
    -0.08
    SizeMode
    -0.07
    ç´¯äºĨ
    -0.07
    -May
    -0.07
    çļĦä¸Ģå®ļ
    -0.07
    POSITIVE LOGITS
    å¹³åĿĩ
    0.14
    å¹³åĿĩæ¯ı
    0.14
     average
    0.13
    çļĦå¹³åĿĩ
    0.12
    å¹´å¹³åĿĩ
    0.12
     بÙĨسبة
    0.12
    约æľī
    0.12
    大约æľī
    0.12
     averages
    0.11
    é«ĺè¾¾
    0.11
    Activations Density 0.670%

    No Known Activations