© 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. 14169
    Prev
    Next
    INDEX
    Explanations

    physical quantities and 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
    Not in Any Lists

    No Comments

    Negative Logits
    æµĵ度为
    -0.07
    å¾µ
    -0.07
    bauer
    -0.07
    å¾ģ
    -0.07
    èİ·å¾ĹåĽ½å®¶
    -0.07
    åľ¨åħ¨åĽ½
    -0.07
    åħ·ä½ĵæŶéĹ´
    -0.06
    ipa
    -0.06
    åħĮ
    -0.06
    bord
    -0.06
    POSITIVE LOGITS
    ä»»éĩį
    0.08
    è¶Ĭ
    0.07
    亦çĦ¶
    0.07
    æį·
    0.07
     Avalanche
    0.07
     Teng
    0.07
    appable
    0.07
    /domain
    0.07
     cÃłng
    0.07
    /configuration
    0.07
    Activations Density 0.034%

    No Known Activations