© 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. 48307
    Prev
    Next
    INDEX
    Explanations

    High-Voltage, Geography, Advent, sprint

    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
    Ú¯ÙĪ
    -0.08
    icing
    -0.08
    gos
    -0.08
    çĶ¸
    -0.08
    igo
    -0.07
    ABC
    -0.07
    วาร
    -0.06
    å¹´å¹´
    -0.06
     Churchill
    -0.06
    .builder
    -0.06
    POSITIVE LOGITS
    aec
    0.08
    ×IJÖ·
    0.07
     Nia
    0.07
     Kear
    0.06
    åŃ¦ä¹łä¸İ
    0.06
    è²
    0.06
    é¢ĺ缮çļĦ
    0.06
    _construct
    0.06
    çѱ
    0.06
    onis
    0.06
    Activations Density 0.022%

    No Known Activations