© 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. 59837
    Prev
    Next
    INDEX
    Explanations

    Boolean circuits and logic gates

    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
    inspace
    -0.08
    atars
    -0.08
     rig
    -0.08
    adius
    -0.07
    creds
    -0.06
     Fic
    -0.06
    upo
    -0.06
     cap
    -0.06
    竹æŀĹ
    -0.06
    纪
    -0.06
    POSITIVE LOGITS
     Boolean
    0.10
    Boolean
    0.09
    表åĨ³
    0.09
     circuits
    0.09
    çĶµè·¯
    0.08
     optimization
    0.08
    çĶµè·¯åĽ¾
    0.08
     mạch
    0.08
    .logic
    0.08
     circuit
    0.08
    Activations Density 0.018%

    No Known Activations