© 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. 10072
    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
    anche
    -0.07
    æī¿
    -0.07
    çķ¥å¾®
    -0.07
    Å«t
    -0.07
    ŀ
    -0.06
    dul
    -0.06
    TickCount
    -0.06
    Dos
    -0.06
    ะ
    -0.06
    arang
    -0.06
    POSITIVE LOGITS
    alom
    0.07
    è¿Łè¿Ł
    0.07
    çĤĬ
    0.07
    ugg
    0.07
    /original
    0.06
    actable
    0.06
    endale
    0.06
     Aprile
    0.06
    åĴĮçĪ¶æ¯į
    0.06
    çļĦåįļ客
    0.06
    Activations Density 0.000%

    No Known Activations