© 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. 44588
    Prev
    Next
    INDEX
    Explanations

    forth, ifter, ither

    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
    fication
    -0.08
    åĽłä¸ºä½ł
    -0.07
    åĽłä¸ºæĪij们
    -0.07
    çļĦä¼ģä¸ļ
    -0.07
    vanced
    -0.07
    andidate
    -0.07
    sene
    -0.07
    ovn
    -0.06
    epam
    -0.06
    åĽłä¸ºå¥¹
    -0.06
    POSITIVE LOGITS
    ither
    0.10
    fter
    0.09
    &R
    0.09
    ле
    0.09
    ith
    0.09
    forth
    0.09
    еÑĢÑĮ
    0.08
    icamente
    0.08
    天ä½ij
    0.08
    ly
    0.08
    Activations Density 0.003%

    No Known Activations