© 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. 60021
    Prev
    Next
    INDEX
    Explanations

    genus or family classification

    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
    éļıæĦıçļĦ
    -0.06
    atap
    -0.06
    .Symbol
    -0.06
    æķĪ
    -0.06
    à¸Ĺัà¹Īว
    -0.06
    éħįåIJĪ
    -0.06
    èįŁ
    -0.06
    çĶ¨å®Į
    -0.06
    饱满
    -0.06
    严äºİ
    -0.06
    POSITIVE LOGITS
     subgroup
    0.10
     ÑģемейÑģÑĤва
    0.10
    éŨ类
    0.09
    æĢ»åı°
    0.09
     Abteilung
    0.09
    大类
    0.08
     genus
    0.08
    æ¯ĶåĪ©
    0.08
    对æѤä¸įæī¿æĭħä»»ä½ķ
    0.08
     grupo
    0.08
    Activations Density 0.210%

    No Known Activations