© 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. 49347
    Prev
    Next
    INDEX
    Explanations

    radiation protection and exposure

    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
    llib
    -0.08
    åĬłæĭī
    -0.07
    å¼Ĥ
    -0.07
    ä¸Ģæ°Ķ
    -0.07
    çĤľ
    -0.07
    ç·¯
    -0.07
    è¢«ä¾ĽåºĶåķĨ
    -0.06
    æĿ¥ç¨¿
    -0.06
    .lift
    -0.06
    traits
    -0.06
    POSITIVE LOGITS
     radiation
    0.13
     Radiation
    0.12
     exposures
    0.11
     shielding
    0.11
     exposure
    0.11
     radioactive
    0.10
    è¾IJå°Ħ
    0.10
    éĺ²æĬ¤
    0.10
     Exposure
    0.09
     hazard
    0.09
    Activations Density 0.056%

    No Known Activations