© 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. 58140
    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
     Poli
    -0.08
    ering
    -0.07
    .equalsIgnoreCase
    -0.07
    erver
    -0.07
    çľŁè°Ľ
    -0.07
    itung
    -0.07
    onos
    -0.06
    ober
    -0.06
    ä¹Łå¹¶éĿŀ
    -0.06
     ind
    -0.06
    POSITIVE LOGITS
    mmas
    0.08
    æ¿
    0.07
    è¯ģæĺİ
    0.07
    omatis
    0.07
    oupon
    0.07
    èªįå®ļ
    0.07
     Levine
    0.06
    èŃīæĺİ
    0.06
     affirm
    0.06
    è¯ģ
    0.06
    Activations Density 0.000%

    No Known Activations