© 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. 61906
    Prev
    Next
    INDEX
    Explanations

    desert climates and features

    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
    æ·Ĩ
    -0.09
    涵
    -0.08
     filet
    -0.08
    æ±Łæ°´
    -0.07
    jern
    -0.07
    æ±Łè·¯
    -0.07
    ä¸īéĢļ
    -0.07
    æī¿
    -0.07
    baut
    -0.07
    -metadata
    -0.07
    POSITIVE LOGITS
    å¹²æű
    0.17
     desert
    0.16
    å¹²çĩ¥
    0.16
    缺水
    0.15
    æ²Ļæ¼ł
    0.15
     dry
    0.15
    dry
    0.13
    èįĴæ¼ł
    0.13
     Desert
    0.13
    ä¹¾çĩ¥
    0.13
    Activations Density 0.156%

    No Known Activations