© 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. 14129
    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
    sWith
    -0.10
    ation
    -0.10
    -fashioned
    -0.09
    精彩åĨħ容
    -0.09
    ÏĤ
    -0.09
    rena
    -0.08
    Ø©
    -0.08
    ë°ĽìĿĢ
    -0.08
    راض
    -0.08
    penas
    -0.08
    POSITIVE LOGITS
    er
    0.10
    culp
    0.08
    ç»Ŀ伦
    0.08
    æ¸ħæ¥ļ
    0.08
    (es
    0.08
     enough
    0.08
    æĺİäºĨ
    0.08
    åħ¥å¾®
    0.07
     اÙĦÙħعاÙĦÙħ
    0.07
    度é«ĺ
    0.07
    Activations Density 0.000%

    No Known Activations