© 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. 55476
    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
    å°Ķé¡¿
    -0.09
    æĶ¿æ²»å±Ģ
    -0.08
    eshire
    -0.06
    ListItem
    -0.06
    çº¿åĽ¾
    -0.06
    มาà¸ģ
    -0.06
    çİīæłij
    -0.06
    usif
    -0.06
    ä½ıè¡Į
    -0.06
     ul
    -0.06
    POSITIVE LOGITS
    åºĶæīĭ
    0.07
    ayment
    0.07
    -ignore
    0.07
    __:
    0.07
    讨
    0.07
     bounty
    0.07
    abaj
    0.07
     Soh
    0.07
    isine
    0.07
     kese
    0.07
    Activations Density 0.000%

    No Known Activations