© 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. 16988
    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
     retribu
    -0.09
    crimin
    -0.09
     notoriously
    -0.08
    éħĹ
    -0.08
    [email
    -0.08
     Zür
    -0.08
     Fakta
    -0.08
    就走
    -0.08
    Dot
    -0.08
    AtPath
    -0.08
    POSITIVE LOGITS
     liken
    0.07
    -like
    0.07
     metaphor
    0.07
    æĻĵ举
    0.07
     imagined
    0.07
     metaph
    0.06
    åĸĦ
    0.06
     lived
    0.06
     align
    0.06
    âĢij
    0.06
    Activations Density 0.000%

    No Known Activations