© 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. 2950
    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
    ulp
    -0.08
    ÑģобÑĭ
    -0.08
    å°ĶèĴĻ
    -0.08
    णà¥Ģ
    -0.08
    ãĥ¬ãĥ³ãĤ¸
    -0.07
     ìĤ¬ìľł
    -0.07
    accia
    -0.07
    EntryPoint
    -0.07
    ante
    -0.07
    loom
    -0.07
    POSITIVE LOGITS
    é¦ĸåħĪ
    0.07
    sson
    0.07
     first
    0.07
     xét
    0.07
    æ¨
    0.06
    allo
    0.06
    0.06
     :
    0.06
    ATER
    0.06
    chw
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.