© 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. 49243
    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
    onge
    -0.08
    inux
    -0.07
    দি
    -0.07
    Subsystem
    -0.07
    è·¯éĢı
    -0.07
    amina
    -0.07
    å¢ŀçĶŁ
    -0.07
    æł¹
    -0.07
    sembl
    -0.06
    ×ķ×ij×Ķ
    -0.06
    POSITIVE LOGITS
    chel
    0.08
    ä¸įçĪ½
    0.07
    rieb
    0.07
    ger
    0.07
    iloc
    0.06
    etti
    0.06
     chung
    0.06
    æĪijçļĦ人
    0.06
    ÑĪнÑĭÑħ
    0.06
    读åĪ°
    0.06
    Activations Density 0.000%

    No Known Activations