© 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. 801
    Prev
    Next
    INDEX
    Explanations

    metric space

    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
    targets
    -0.07
    WithContext
    -0.07
    çIJĨå·¥åѦéĻ¢
    -0.07
     trình
    -0.07
    ÙĥÙĪر
    -0.07
    æİ¥åĪ°
    -0.06
     ARRAY
    -0.06
    reak
    -0.06
    elaar
    -0.06
    kes
    -0.06
    POSITIVE LOGITS
     defining
    0.08
    度éĩı
    0.08
    åĬłæĸ¯
    0.07
    EGA
    0.07
    æŁ»
    0.07
    _metric
    0.07
    çĽ¸å®¹
    0.07
    ehme
    0.07
     metr
    0.07
    Metric
    0.07
    Activations Density 0.009%

    No Known Activations