© 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. 61914
    Prev
    Next
    INDEX
    Explanations

    measurement

    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
    er
    -0.13
    à±ģ
    -0.11
    çĦ¶æĺ¯
    -0.09
    oftware
    -0.09
    pel
    -0.09
    o
    -0.09
    erÃŃa
    -0.09
    heimer
    -0.09
    oja
    -0.08
    imately
    -0.08
    POSITIVE LOGITS
    ers
    0.08
    leon
    0.07
    ä¸Ńå¿ĥåĮ»éĻ¢
    0.07
    å¤ļãģĦ
    0.07
    enticate
    0.07
    ting
    0.07
    翼翼
    0.07
    /testing
    0.07
    SSION
    0.07
    ary
    0.07
    Activations Density 0.034%

    No Known Activations