© 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. 26905
    Prev
    Next
    INDEX
    Explanations

    main (.cpp)

    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
    incer
    -0.08
    integr
    -0.08
    åĽ½åįİ
    -0.08
    ernal
    -0.08
    egov
    -0.08
    eric
    -0.08
    ernel
    -0.08
    ovar
    -0.07
    hto
    -0.07
    æ±Łæµ·
    -0.07
    POSITIVE LOGITS
     instead
    0.09
     invece
    0.08
     itself
    0.08
    instead
    0.08
     Instead
    0.07
    Instead
    0.07
    æīį对
    0.07
     fol
    0.07
    ãģĤãģı
    0.07
    è¿Ļæīįæĺ¯
    0.06
    Activations Density 0.017%

    No Known Activations