© 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. 7086
    Prev
    Next
    INDEX
    Explanations

    resolve, disclose, observe, predating

    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
    hood
    -0.09
     ones
    -0.07
    asaan
    -0.07
    ATION
    -0.07
    endientes
    -0.06
    adays
    -0.06
    лÑĭÒĽ
    -0.06
    evole
    -0.06
    Ø©
    -0.06
    itis
    -0.06
    POSITIVE LOGITS
    å¾Ĺ太
    0.10
    å¾Ĺ好
    0.10
    ither
    0.10
    ut
    0.10
    ilit
    0.09
    ud
    0.09
    åħ¶åIJį
    0.09
    upe
    0.09
    ard
    0.09
    uce
    0.09
    Activations Density 0.171%

    No Known Activations