© 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. 17264
    Prev
    Next
    INDEX
    Explanations

    Oppenheimer approximation

    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
    ä¸Ģè¨Ģ
    -0.07
     mat
    -0.07
    org
    -0.07
    ivor
    -0.06
    åħ·ä½ĵçļĦ
    -0.06
    tim
    -0.06
    semb
    -0.06
     оÑĢÑĥ
    -0.06
    èµĭ
    -0.06
    毫æĹł
    -0.06
    POSITIVE LOGITS
    è¿ijä¼¼
    0.15
     approximation
    0.13
     approx
    0.12
    _approx
    0.12
     Approx
    0.11
     negligible
    0.11
    æĺ¯å°ı
    0.11
    /small
    0.10
    忽çķ¥
    0.10
    ä¸Ģ个å°ı
    0.10
    Activations Density 0.035%

    No Known Activations