© 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. 10642
    Prev
    Next
    INDEX
    Explanations

    celebration honoring fathers

    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
    اÙĤ
    -0.10
    ä¹±æĶ¾
    -0.09
    rightness
    -0.09
    gern
    -0.09
    toa
    -0.09
     magnÃŃ
    -0.09
     encab
    -0.09
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.09
    ãĥ¬ãĤ¹ãĥĪ
    -0.09
    ExceptionHandler
    -0.09
    POSITIVE LOGITS
    ↵
    0.08
    ...
    0.07
     l
    0.07
    l
    0.07
     s
    0.07
    �
    0.07
    v
    0.06
    '
    0.06
     w
    0.06
    \n
    0.06
    Activations Density 0.285%

    No Known Activations