© 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. 58954
    Prev
    Next
    INDEX
    Explanations

    code keywords (`await`, `if`, `return`, `private`, `let`)

    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
    icke
    -0.08
    osso
    -0.08
    سÙĬ
    -0.07
    رس
    -0.07
    irá
    -0.07
    othi
    -0.07
     specialised
    -0.06
    Que
    -0.06
    re
    -0.06
     charg
    -0.06
    POSITIVE LOGITS
    å¹ħ
    0.07
    ä¹ĭæ¯į
    0.06
    ŀ
    0.06
    ALLOW
    0.06
    å±Ī
    0.06
    cles
    0.06
    arre
    0.06
    leo
    0.06
     Noticed
    0.06
    å±Ĭ
    0.06
    Activations Density 0.001%

    No Known Activations