© 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. 7104
    Prev
    Next
    INDEX
    Explanations

    unintended or unwanted consequences

    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
    emun
    -0.09
    ipan
    -0.08
    ÙĨائ
    -0.08
    полÑı
    -0.08
    åħ»é¢ľ
    -0.08
    ستاÙĨÛĮ
    -0.07
    å¾Ĺä¸Ĭ
    -0.07
    _DM
    -0.07
    orio
    -0.07
    ffin
    -0.07
    POSITIVE LOGITS
     unintended
    0.15
     unwanted
    0.14
     undes
    0.11
     unintention
    0.10
     undesirable
    0.10
    é»ĺ认
    0.09
     default
    0.09
    undes
    0.09
     unless
    0.09
    åģı
    0.08
    Activations Density 0.442%

    No Known Activations