© 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. 34787
    Prev
    Next
    INDEX
    Explanations

    support structure

    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
    Not in Any Lists

    No Comments

    Negative Logits
    yron
    -0.08
    帮åĬ©å¤§å®¶
    -0.08
    /entities
    -0.07
     semiclass
    -0.07
     Saved
    -0.07
    å½
    -0.07
    åĽŃåĨħ
    -0.07
    -sized
    -0.07
    éħ¸çļĦ
    -0.07
    é£Ļåįĩ
    -0.07
    POSITIVE LOGITS
    约æĿŁ
    0.09
    _constraints
    0.08
     constraint
    0.08
    çī¢åĽº
    0.08
    á»Ŀ
    0.07
    Constraint
    0.07
     constraints
    0.07
     restraint
    0.07
    é½IJé½IJ
    0.07
    åĪļæĢ§
    0.07
    Activations Density 0.006%

    No Known Activations