© 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. 16844
    Prev
    Next
    INDEX
    Explanations

    graphs and paths

    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
    à¹Ħว
    -0.07
     gradu
    -0.07
    èģª
    -0.07
    æŃĮè¿·
    -0.07
    æŀľçļ®
    -0.07
    -0.07
    appoint
    -0.07
    éŀĺ
    -0.06
    åĤ¨å¤ĩ
    -0.06
     sor
    -0.06
    POSITIVE LOGITS
     Fey
    0.10
     diagrams
    0.09
     diagram
    0.08
    Diagram
    0.08
     Diagram
    0.08
     propag
    0.08
    åѤ
    0.08
     disconnected
    0.08
    è´¡çĮ®
    0.08
     connecting
    0.08
    Activations Density 0.012%

    No Known Activations