© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9628
    Prev
    Next
    INDEX
    Explanations

    types of levels or intensity

    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
    enner
    -0.07
    ÐIJÐŀ
    -0.07
    ÙĩÙIJ
    -0.07
    icidade
    -0.07
    avage
    -0.07
    宿
    -0.07
    iedade
    -0.07
    çµIJ
    -0.07
    hw
    -0.07
    跳跳
    -0.07
    POSITIVE LOGITS
    imate
    0.07
    inet
    0.07
    ìłģìĿ¸
    0.07
    æ·
    0.07
    å±ĤéĿ¢çļĦ
    0.06
    äºİäºĭ
    0.06
    
    0.06
    ained
    0.06
    æ©
    0.06
    contexts
    0.06
    Activations Density 0.074%

    No Known Activations