© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34888
    Prev
    Next
    INDEX
    Explanations

    matrix and host relationships

    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
    Negative Logits
     ess
    -0.07
    Äĺ
    -0.06
    Quantity
    -0.06
    离æĪij们
    -0.06
     Quantity
    -0.06
    åĺ´ä¸Ĭ
    -0.06
    çİ°åľºç¡®è®¤
    -0.06
     Roose
    -0.06
    çĶĺéľ²
    -0.06
    ิà¹īà¸ĩ
    -0.06
    POSITIVE LOGITS
     surrounding
    0.10
    çĶŁçĶŁ
    0.09
    宿主
    0.08
    æķ´ä½ĵçļĦ
    0.08
     weakest
    0.08
    åĿļ强
    0.08
    骨æŀ¶
    0.07
    æľ¬èī²
    0.07
    hosts
    0.07
     backbone
    0.07
    Activations Density 0.057%

    No Known Activations