© 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. 63616
    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
    ry
    -0.07
    ra
    -0.07
    mand
    -0.07
    ians
    -0.07
    vig
    -0.06
    çijľ
    -0.06
    ä¸ĭ
    -0.06
    n
    -0.06
    лона
    -0.06
    аÑĤа
    -0.06
    POSITIVE LOGITS
    ä¹ĭ以
    0.09
    Bindable
    0.08
    FIELDS
    0.08
    大åĪ©
    0.08
    ÃŃso
    0.08
    onder
    0.08
    çļĦä¸Ģå¹´éĩĮ
    0.07
    Ù°
    0.07
     iepazÄ«Å¡anÄģs
    0.07
     illet
    0.07
    Activations Density 0.000%

    No Known Activations