© 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. 44380
    Prev
    Next
    INDEX
    Explanations

    asteroid, asteroids, and related celestial bodies

    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
    èĤ
    -0.08
     Bleu
    -0.07
    åģľä¸ļ
    -0.07
     Breitbart
    -0.07
    enth
    -0.07
    é±¼
    -0.07
    æµ´
    -0.07
     bedside
    -0.06
    olec
    -0.06
    ount
    -0.06
    POSITIVE LOGITS
     asteroid
    0.12
     asteroids
    0.11
     crater
    0.08
    uduk
    0.08
    ampo
    0.08
    ¾
    0.08
     classification
    0.08
    åĪĨç±»åı·
    0.08
     planet
    0.07
    åĺīå¹´åįİ
    0.07
    Activations Density 0.040%

    No Known Activations