© 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. 42309
    Prev
    Next
    INDEX
    Explanations

    goddess names and religious terms

    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
    天价
    -0.07
    åĴĮå°ļ
    -0.06
    å±ħ士
    -0.06
    оба
    -0.06
    Mate
    -0.06
     opt
    -0.06
    éĻĭ
    -0.06
    è¶Ł
    -0.06
    ç¾ļ
    -0.06
    èĮĥ
    -0.06
    POSITIVE LOGITS
    æİĮ管
    0.12
     worsh
    0.10
     overseeing
    0.09
    形象åĴĮ
    0.09
     underworld
    0.09
    çļĦ形象
    0.09
     oversees
    0.09
    巡游
    0.09
     deity
    0.09
    èģĮèĥ½
    0.08
    Activations Density 0.079%

    No Known Activations