© 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. 62874
    Prev
    Next
    INDEX
    Explanations

    before phrases

    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
     kho
    -0.08
     бокÑĥ
    -0.07
    çħĮ
    -0.07
    _beg
    -0.07
    第ä¸Ģå¹´
    -0.07
    ר×ķף
    -0.07
    é·
    -0.07
    说è¯ĿäºĨ
    -0.07
    -progress
    -0.07
    ä¸Ģå¹´æĿ¥
    -0.07
    POSITIVE LOGITS
     before
    0.12
    before
    0.12
     Before
    0.10
    Before
    0.10
     antes
    0.10
     ÙĤبÙĦ
    0.10
    (before
    0.09
     sebelum
    0.09
     Sebelum
    0.09
     BEFORE
    0.08
    Activations Density 0.154%

    No Known Activations