© 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. 57814
    Prev
    Next
    INDEX
    Explanations

    antenna arrays

    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
    å´©
    -0.08
    å®ķ
    -0.08
    cius
    -0.07
    oons
    -0.07
    äumt
    -0.07
     Crash
    -0.07
     Bracket
    -0.07
    oxic
    -0.07
    andum
    -0.07
    bidden
    -0.06
    POSITIVE LOGITS
     antennas
    0.10
    æĶ¶åıij
    0.10
    éĺµåĪĹ
    0.09
     Direction
    0.09
     antenna
    0.09
    天线
    0.08
     directional
    0.08
    罩
    0.08
    磩éĺµ
    0.08
     spoof
    0.08
    Activations Density 0.031%

    No Known Activations