© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44587
    Prev
    Next
    INDEX
    Explanations

    eliminate

    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
    Negative Logits
    aversable
    -0.08
    ghi
    -0.08
    ETTA
    -0.07
    unya
    -0.07
     tản
    -0.07
    ÙĨج
    -0.07
    µľ
    -0.07
    itan
    -0.07
    è·Ľ
    -0.07
    cardo
    -0.07
    POSITIVE LOGITS
     technically
    0.08
     Elim
    0.07
    ä¸ĢéĹ´
    0.07
     deci
    0.07
    .Suppress
    0.07
    Elim
    0.06
     smash
    0.06
    æĬĢ
    0.06
     eliminate
    0.06
    éļĶæĸŃ
    0.06
    Activations Density 0.002%

    No Known Activations