© 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. 62029
    Prev
    Next
    INDEX
    Explanations

    superlative adjectives

    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
    CHED
    -0.07
    etch
    -0.07
    åħ¶çī¹å¾ģ
    -0.07
    çĥŃ线çĶµè¯Ŀ
    -0.07
    æīĢ使çĶ¨çļĦ
    -0.07
    æīĢçĶ¨çļĦ
    -0.06
    é»ŀæĪij
    -0.06
    éĩĩ
    -0.06
     Ready
    -0.06
    hod
    -0.06
    POSITIVE LOGITS
    -priced
    0.08
     among
    0.08
    èİ«è¿ĩäºİ
    0.07
    -ranked
    0.07
     davon
    0.07
     ÑģÑĢеди
    0.07
     ×ij×Ļ×ķתר
    0.07
    -ranking
    0.07
     contenders
    0.07
    à¤Ńव
    0.07
    Activations Density 0.040%

    No Known Activations