© 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. 17538
    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
    ALS
    -0.06
    als
    -0.06
    à¸ı
    -0.06
    egi
    -0.06
    ¡°
    -0.06
    à¸İ
    -0.06
    年头
    -0.06
    ee
    -0.06
    åħ¬æīĢ
    -0.06
    å¤ļä¸ªåĽ½å®¶åĴĮåľ°åĮº
    -0.06
    POSITIVE LOGITS
    æľ¬çº§
    0.07
    åıĤèµĽéĢīæīĭ
    0.07
    è³ĩ
    0.07
    æĪĸæľª
    0.07
    ائب
    0.07
    ²
    0.07
     pragma
    0.07
    chap
    0.07
    tlement
    0.07
    imately
    0.07
    Activations Density 0.000%

    No Known Activations