© 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. 29156
    Prev
    Next
    INDEX
    Explanations

    microwave antenna coaxial cable

    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
    æľºåĪ¶
    -0.07
    亲
    -0.07
    ä¸ī峡
    -0.07
    滤èĬ¯
    -0.07
    irro
    -0.06
    ä¸ĭå¿ĥ
    -0.06
    æĿłæĿĨ
    -0.06
     kib
    -0.06
    kaan
    -0.06
    çī¹å°Ķ
    -0.06
    POSITIVE LOGITS
     impedance
    0.12
    éĺ»æĬĹ
    0.11
     Microwave
    0.11
    rowave
    0.10
    è°IJæĮ¯
    0.10
     antenna
    0.10
     coax
    0.10
     antennas
    0.10
    微波
    0.09
     microwave
    0.09
    Activations Density 0.044%

    No Known Activations