© 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. 4687
    Prev
    Next
    INDEX
    Explanations

    acceleration enabled settings

    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
    /tasks
    -0.07
     HACK
    -0.07
    åħ·æľīè¾ĥ强çļĦ
    -0.07
     NES
    -0.07
     minecraft
    -0.07
    æĭŁå»º
    -0.06
    çĻ»å½ķåIJİ
    -0.06
    èµ·å±ħ
    -0.06
    åĨįä¸ī
    -0.06
    ilton
    -0.06
    POSITIVE LOGITS
    -enabled
    0.13
    _ENABLED
    0.12
    _enabled
    0.12
     enabled
    0.11
    enabled
    0.11
    Enabled
    0.11
     Enabled
    0.10
    .enabled
    0.09
    -enh
    0.09
     implemented
    0.09
    Activations Density 0.358%

    No Known Activations