© 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. 778
    Prev
    Next
    INDEX
    Explanations

    arithmetic calculations

    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
    otts
    -0.08
    OfWork
    -0.08
    ogat
    -0.08
    éĿŀ常åĩºèī²
    -0.08
    nissen
    -0.07
    çĽ¸å¯¹è¾ĥä½İ
    -0.07
    ÙĪرÙĥ
    -0.07
     trien
    -0.07
    èĩ³åħ³
    -0.07
     **—
    -0.07
    POSITIVE LOGITS
     ê¼
    0.07
    argo
    0.07
    uschen
    0.06
     "
    0.06
    æĪª
    0.06
    reno
    0.06
    èĢĥ
    0.06
    è¿Ķ
    0.06
    謹
    0.06
     rains
    0.06
    Activations Density 0.071%

    No Known Activations