© 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. 14296
    Prev
    Next
    INDEX
    Explanations

    battery and storage

    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
    åĸ·åļı
    -0.08
    èĪŀèĢħ
    -0.07
    azzi
    -0.06
     ÑĤоп
    -0.06
     Gust
    -0.06
    æīĵåĸ·åļı
    -0.06
    ä¸ĩ件
    -0.06
    æģĻ
    -0.06
    å¤ļæł·
    -0.06
    å°½éĩıéĢīæĭ©
    -0.06
    POSITIVE LOGITS
    æ¶
    0.09
    èĵĦçĶµæ±ł
    0.09
     állapot
    0.08
    æŃ£æŀģ
    0.08
    aporte
    0.08
    ools
    0.08
    çĶµçĵ¶
    0.08
    ież
    0.07
     convoy
    0.07
    aintenance
    0.07
    Activations Density 0.032%

    No Known Activations