© 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. 26741
    Prev
    Next
    INDEX
    Explanations

    { } structures

    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
    azer
    -0.08
    ouns
    -0.07
    erras
    -0.07
    orial
    -0.07
    adr
    -0.07
    yps
    -0.06
    oji
    -0.06
    inkt
    -0.06
    yr
    -0.06
    ordial
    -0.06
    POSITIVE LOGITS
    ccione
    0.07
    æĹłå¿Į
    0.07
    ä½Ĩä¸įéĻIJäºİ
    0.07
    ä¹Łè®¸ä¼ļ
    0.07
    enga
    0.07
    åŁŁçļĦ
    0.07
    çĻ¾è®¡
    0.06
    ninger
    0.06
    bourg
    0.06
    JKLM
    0.06
    Activations Density 0.001%

    No Known Activations