© 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. 14835
    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
    åĩĨ
    -0.08
     Ayd
    -0.08
    cky
    -0.08
    æºĸ
    -0.08
    icken
    -0.08
    ((&
    -0.07
    াà¦ĩ
    -0.07
    yon
    -0.07
    !("
    -0.07
    ickers
    -0.07
    POSITIVE LOGITS
    ourt
    0.08
    å°ıèıľ
    0.07
    ormsg
    0.07
    åĺ²
    0.07
    åĨħåIJ«
    0.06
    orter
    0.06
    è¯Ĺæĸĩ
    0.06
     containing
    0.06
    åIJijåħļ
    0.06
     Erf
    0.06
    Activations Density 0.000%

    No Known Activations