© 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. 19108
    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
    æĪĸå°ij
    -0.09
    irt
    -0.08
    æĺ¯ä¸Ģ个人
    -0.07
    pto
    -0.07
    調éģĶ
    -0.07
    weif
    -0.07
    voud
    -0.07
    anze
    -0.07
    δί
    -0.07
    avour
    -0.07
    POSITIVE LOGITS
    å®ļä¼ļ
    0.07
     again
    0.07
    åıĪä¸Ģ次
    0.07
    åıĪä¸Ģ个
    0.07
    ij
    0.06
    lal
    0.06
    åĨįä¸Ģ次
    0.06
    Instance
    0.06
     Instance
    0.06
    isi
    0.06
    Activations Density 0.000%

    No Known Activations