© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 38334
    Prev
    Next
    INDEX
    Explanations

    language names and dialects

    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
    amba
    -0.07
    illis
    -0.07
     latino
    -0.07
    ikä
    -0.07
    ikli
    -0.07
    大象
    -0.07
    声èī²
    -0.06
    ä¸İæľ¬
    -0.06
    èĬŃ
    -0.06
     contro
    -0.06
    POSITIVE LOGITS
     dialect
    0.10
     extinct
    0.08
     proto
    0.08
     vowels
    0.07
     east
    0.07
    åĪĨåĮĸ
    0.07
     north
    0.07
     west
    0.07
     variant
    0.07
     mainland
    0.07
    Activations Density 0.097%

    No Known Activations