© 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. 34827
    Prev
    Next
    INDEX
    Explanations

    active surveillance, microcurrent therapy, data locality, self-perception theory

    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
    ï¾ŀ
    -0.08
    itel
    -0.08
    ÅĦ
    -0.07
     ÐIJпÑĢе
    -0.07
    _VARS
    -0.07
    Ø®
    -0.07
    ר×ĺ
    -0.07
    zeti
    -0.07
    ìn
    -0.07
    éĥİ
    -0.07
    POSITIVE LOGITS
    海天
    0.06
     \"
    0.06
     [âĢ¦]
    0.06
    icz
    0.06
    ntax
    0.06
     [...]
    0.06
    é¾Ļåĩ¤
    0.06
    óta
    0.06
    ÏĢάν
    0.06
     sue
    0.05
    Activations Density 1.166%

    No Known Activations