© 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. 41776
    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
    kot
    -0.08
    该æĢİä¹Ī
    -0.07
    cwd
    -0.07
    leben
    -0.07
    εÏħ
    -0.07
    VECTOR
    -0.07
    Ľ°
    -0.07
    ä½łå¾Ĺ
    -0.07
     usur
    -0.07
    第äºĮåįģ
    -0.07
    POSITIVE LOGITS
    å¹Į
    0.07
     ['.
    0.07
    群
    0.07
     Patron
    0.07
     Classifier
    0.07
    å¿Ĺæĺİ
    0.06
    undra
    0.06
    chs
    0.06
    åIJ¸è¡Ģ
    0.06
     Hopkins
    0.06
    Activations Density 0.000%

    No Known Activations