© 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. 22705
    Prev
    Next
    INDEX
    Explanations

    carbon dioxide and storage

    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
     biss
    -0.08
    ogonal
    -0.08
    èij£äºĭ
    -0.07
    rics
    -0.07
    é£Łåĵģåį«çĶŁ
    -0.07
    vah
    -0.07
     écl
    -0.07
    å¤ĸå¸ģ
    -0.06
    ä¸īéĿ¢
    -0.06
    äºĪåijĬ
    -0.06
    POSITIVE LOGITS
     carbon
    0.12
    碳
    0.11
     Carbon
    0.10
    carbon
    0.10
    Carbon
    0.10
     carbono
    0.09
    æ¯ıå¹´
    0.09
     hấp
    0.09
    碳ä¸ŃåĴĮ
    0.09
     karbon
    0.09
    Activations Density 0.019%

    No Known Activations