© 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. 39265
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     dahil
    -0.09
    weise
    -0.08
    nowrap
    -0.08
    رÙĤ
    -0.08
    neau
    -0.08
    ignano
    -0.08
    iglio
    -0.08
    Continua
    -0.07
    æ°´æµĴ
    -0.07
    ansa
    -0.07
    POSITIVE LOGITS
     sol
    0.06
    sol
    0.06
    æ¦Ĥè¦ģ
    0.06
    åĮ£
    0.06
    ↵↵
    0.06
    满åłĤ
    0.06
     tu
    0.06
    ï¸
    0.06
    sak
    0.06
    èĨ³
    0.05
    Activations Density 0.000%

    No Known Activations