© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 55798
    Prev
    Next
    INDEX
    Explanations

    approximation and estimation

    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
     uniquely
    -0.07
    çĭ¬ä¸ĢæĹłäºĮçļĦ
    -0.07
    .finished
    -0.07
    çĭ¬ä¸ĢæĹłäºĮ
    -0.07
    Handled
    -0.06
     eindeutig
    -0.06
    èĩ£
    -0.06
    ç¡®ä¿Ŀ
    -0.06
     Ñĥника
    -0.06
     encountered
    -0.06
    POSITIVE LOGITS
     approximation
    0.16
    è¿ijä¼¼
    0.14
     approx
    0.14
     Approx
    0.13
    _approx
    0.13
     approximate
    0.12
     estimate
    0.12
    approx
    0.11
     пÑĢибли
    0.11
     aproxima
    0.11
    Activations Density 0.025%

    No Known Activations