© 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. 7584
    Prev
    Next
    INDEX
    Explanations

    reverse / -re

    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
    -0.08
    ocker
    -0.08
     Usai
    -0.08
    åĵĪæĭī
    -0.07
    æĻ¤
    -0.07
    第ä¸Ģåį°è±¡
    -0.07
    beutel
    -0.07
    elos
    -0.07
    åĤ¬çĶŁ
    -0.07
     firsthand
    -0.07
    POSITIVE LOGITS
    ×IJ×ķת
    0.06
     lautet
    0.06
    æĭĨåĪĨ
    0.06
    ::-
    0.06
    witz
    0.06
     revers
    0.06
     revision
    0.06
    æĸ¥
    0.06
    ÙĪÙĬØ©
    0.06
     reverse
    0.06
    Activations Density 0.001%

    No Known Activations