© 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. 54930
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with powers

    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
    itra
    -0.07
    abia
    -0.07
    aska
    -0.07
    _LANG
    -0.06
    :str
    -0.06
    åħīæĺ¯
    -0.06
    idal
    -0.06
    æĪĸå°ij
    -0.06
    Ùģاع
    -0.06
    æľĢ主è¦ģ
    -0.06
    POSITIVE LOGITS
    -ok
    0.08
    ABCDEFG
    0.08
     ÃĹ
    0.08
    åĽłåŃIJ
    0.08
    ÃĹ
    0.08
    èĩ´
    0.08
    ][(
    0.07
    çª
    0.07
     condol
    0.07
    ==(
    0.07
    Activations Density 0.054%

    No Known Activations