© 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. 43454
    Prev
    Next
    INDEX
    Explanations

    aniline derivatives

    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
    çĶļèĢħ
    -0.08
    æĸĩçIJĨ
    -0.07
    bran
    -0.07
    åłĤåłĤ
    -0.07
    èIJ½äºĨ
    -0.07
    _ARGUMENT
    -0.07
     Nvidia
    -0.07
    orage
    -0.07
    åľ°éľĩ
    -0.07
    山路
    -0.07
    POSITIVE LOGITS
     pisc
    0.07
    åĩī
    0.07
     Meer
    0.07
    ä¼ij
    0.06
    yas
    0.06
    Pixels
    0.06
     Merch
    0.06
     Shib
    0.06
     Bangladesh
    0.06
     usher
    0.06
    Activations Density 0.011%

    No Known Activations