© 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. 52060
    Prev
    Next
    INDEX
    Explanations

    operators and separators

    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
    梯
    -0.07
    es
    -0.06
    rawl
    -0.06
    å«ī
    -0.06
    çĭ¼
    -0.06
    âĢ¦
    -0.06
    çĮ
    -0.05
    Ó¯
    -0.05
    å¦ĤæĦı
    -0.05
    çĪ½
    -0.05
    POSITIVE LOGITS
    tene
    0.08
    achr
    0.08
    æ´»åĬ¨åľ¨
    0.08
    anine
    0.08
    blo
    0.08
    ept
    0.08
    ÙĪØŃ
    0.07
    åħĭç¦ı
    0.07
    </tool_call>
    0.07
    صد
    0.07
    Activations Density 0.002%

    No Known Activations