© 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. 56926
    Prev
    Next
    INDEX
    Explanations

    if it were

    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
    elier
    -0.08
    èµ
    -0.08
    apun
    -0.08
    новиÑĩ
    -0.08
    apura
    -0.07
    bach
    -0.07
    azgo
    -0.07
    çļĦ人工
    -0.07
    ä¸įæ¯Ķ
    -0.07
    å°ıèĢĮ
    -0.07
    POSITIVE LOGITS
     wouldn
    0.10
     wären
    0.09
     would
    0.09
    would
    0.09
     sarebbero
    0.08
     olisi
    0.08
    è¿Ļä¹Īç®Ģåįķ
    0.08
     wäre
    0.08
     Would
    0.07
     hätte
    0.07
    Activations Density 0.034%

    No Known Activations