© 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. 20469
    Prev
    Next
    INDEX
    Explanations

    file extensions (.h, .cpp, .swift)

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    \"
    -0.07
    otto
    -0.06
    /********
    -0.06
     Casal
    -0.06
    åĩŃåĢŁåħ¶
    -0.06
     suspect
    -0.05
    gis
    -0.05
     chr
    -0.05
    æľ¬æĸĩå°Ĩä»İ
    -0.05
    {\"
    -0.05
    POSITIVE LOGITS
    .swift
    0.09
    å¾·ç½Ĺ
    0.08
     eskort
    0.08
    Ùħص
    0.08
    è§ģ人
    0.08
    اÙħÙĨ
    0.08
    chsel
    0.07
    deaux
    0.07
    òng
    0.07
    æĶ¶èĹıæľ¬ç«Ļ
    0.07
    Activations Density 0.109%

    No Known Activations