© 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. 8728
    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
    cross
    -0.08
    åĩĨ
    -0.08
    éĢļçĶ¨çļĦ
    -0.07
    åĽ¾æĸ¯
    -0.07
    éĢļçĶ¨
    -0.07
     General
    -0.07
    åIJĮåı°
    -0.07
    .cross
    -0.07
     prob
    -0.07
     general
    -0.07
    POSITIVE LOGITS
    ivia
    0.08
    ãģŁãģ£ãģ·ãĤĬ
    0.08
    åĮ£
    0.08
    è±Ĭå¯Į
    0.08
    çĽ£å¯Ł
    0.07
     koc
    0.07
     sisa
    0.07
    丰å¯ĮçļĦ
    0.07
    ãģĵãĤĮãģ§
    0.07
    åī©ä½ĻçļĦ
    0.07
    Activations Density 0.000%

    No Known Activations