© 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. 23562
    Prev
    Next
    INDEX
    Explanations

    numbers and mathematical operations

    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
    èģĶæĴŃ
    -0.08
    ä¸įæ¼ı
    -0.08
     ül
    -0.08
    æľīçĶŁ
    -0.08
     unm
    -0.08
    åºĵéĩĮ
    -0.07
    ä»Ģä¹Īåij¢
    -0.07
    æľīåĬł
    -0.07
    ahari
    -0.07
    çĶŁæ°´
    -0.07
    POSITIVE LOGITS
    év
    0.08
     exec
    0.06
    è¦ģä¹Īæĺ¯
    0.06
     iterative
    0.06
    çĭ©
    0.06
    acz
    0.06
    APH
    0.06
    åıĤä¸İåĪ°
    0.06
    å°±æĺ¯æĪijçļĦ
    0.06
    å¦Ļ
    0.06
    Activations Density 0.046%

    No Known Activations