© 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. 62696
    Prev
    Next
    INDEX
    Explanations

    organizations and locations

    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
    peen
    -0.08
    ptes
    -0.08
    etul
    -0.07
    ãģ±
    -0.07
     @}
    -0.07
    uhan
    -0.07
    çī¹åĪ«æĺ¯å¯¹
    -0.07
    itzer
    -0.07
     Loa
    -0.07
    DECL
    -0.07
    POSITIVE LOGITS
    ãĢįãĢģãĢĮ
    0.07
    ï¼īãĢģ
    0.07
    )ãĢģ
    0.07
    ãģĵãģ¨ãĤĦ
    0.07
     priv
    0.07
    ãĢįãĢĮ
    0.06
    ""
    0.06
     ex
    0.06
     ","
    0.06
    .datab
    0.06
    Activations Density 0.002%

    No Known Activations