© 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. 23637
    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
    unga
    -0.08
    大头
    -0.08
    uitar
    -0.08
    å®ļ为
    -0.07
    pecific
    -0.07
    å·¡è§Ĩåijĺ
    -0.07
    illante
    -0.07
    åĪĨé¡ŀ
    -0.07
    çĢļ
    -0.07
    QUE
    -0.07
    POSITIVE LOGITS
    æķ¢è¯´
    0.07
    Incoming
    0.07
    edo
    0.07
    raine
    0.07
    edly
    0.07
     |–
    0.06
    را
    0.06
    EFR
    0.06
     outgoing
    0.06
    微信æī«çłģ
    0.06
    Activations Density 0.000%

    No Known Activations