© 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. 64263
    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
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.11
    activex
    -0.10
    веÑĤа
    -0.09
    eges
    -0.09
    æľ¨æĸ¯
    -0.09
    ä¹IJä¹İ
    -0.09
    ä¸į误
    -0.09
    èĮĥæĸĩç½ij
    -0.09
    ekom
    -0.08
    ummings
    -0.08
    POSITIVE LOGITS
    ritis
    0.07
    0.07
    rium
    0.06
    ç»ıè¿ĩ
    0.06
     specially
    0.06
    çĿ¡ä¸įçĿĢ
    0.06
    æľĶ
    0.06
    年以ä¸Ĭ
    0.05
     disent
    0.05
     nothing
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.