© 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. 16788
    Prev
    Next
    INDEX
    Explanations

    broadcast messages

    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
    nico
    -0.09
    idata
    -0.08
     [[[
    -0.08
    abia
    -0.08
    nett
    -0.08
    ãĥ¼ãĤŃ
    -0.08
    ØŃÙĥاÙħ
    -0.07
     samp
    -0.07
    ابÛĮ
    -0.07
    UNET
    -0.07
    POSITIVE LOGITS
    广æĴŃ
    0.08
    broadcast
    0.08
     ripple
    0.07
    Broadcast
    0.07
     Carly
    0.07
     broadcasts
    0.06
    roadcast
    0.06
     Gau
    0.06
     broadcast
    0.06
    apy
    0.06
    Activations Density 0.005%

    No Known Activations