© 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. 29665
    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
    ...
    -0.08
    çĿĢä»Ģä¹Ī
    -0.07
     taxp
    -0.07
    ä¹ĥ
    -0.07
    arth
    -0.07
    -dot
    -0.06
     menun
    -0.06
    sh
    -0.06
     Pera
    -0.06
     tzv
    -0.06
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.10
    ï¸İ
    0.09
    ÙģÙĪ
    0.08
    ).-
    0.08
     suppl
    0.08
    .appspot
    0.07
    âĢij
    0.07
    ','%
    0.07
    å¯Ŀ室
    0.07
    ï¸ı
    0.07
    Activations Density 0.000%

    No Known Activations