© 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. 48727
    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
    igon
    -0.09
    วà¸Ļ
    -0.07
    天ä¸ĭçļĦ
    -0.07
    zwi
    -0.07
    ilog
    -0.07
    éĺ
    -0.07
    eler
    -0.07
    麹
    -0.06
    èĬľ
    -0.06
    utch
    -0.06
    POSITIVE LOGITS
    scoped
    0.07
    caf
    0.07
    alas
    0.07
    anny
    0.07
    erings
    0.07
    áb
    0.07
    æŀľçĦ¶
    0.07
    cas
    0.06
     alternative
    0.06
    ERING
    0.06
    Activations Density 0.000%

    No Known Activations