© 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. 4426
    Prev
    Next
    INDEX
    Explanations

    electromagnetic spectrum ranges

    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
     chance
    -0.07
    åľ¨æŁIJ
    -0.06
    Ļ
    -0.06
    hoven
    -0.06
    æĺķ
    -0.06
    rita
    -0.06
    vi
    -0.06
    åıªé¡¾
    -0.06
    è´
    -0.06
    åĵī
    -0.05
    POSITIVE LOGITS
    -range
    0.10
    èĮĥåĽ´
    0.10
     диапазоне
    0.10
     вплоÑĤÑĮ
    0.09
    range
    0.09
     range
    0.09
     диапазо
    0.09
     диапаз
    0.09
    ç¯Ħåľį
    0.09
     ranges
    0.09
    Activations Density 0.186%

    No Known Activations