© 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. 44757
    Prev
    Next
    INDEX
    Explanations

    variable, dynamic, generics

    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
    ARC
    -0.07
    ¾
    -0.07
    æ½ľ
    -0.07
    stur
    -0.06
    ru
    -0.06
    å¤©æ±ł
    -0.06
    åĿı
    -0.06
    ç®Ģåįķæĺĵ
    -0.06
    stop
    -0.06
    _dicts
    -0.06
    POSITIVE LOGITS
    ãģ¾ãģ¾ãģ§
    0.09
    以å¾ħ
    0.09
     algebra
    0.09
    缴åĪ°
    0.09
     until
    0.09
    _until
    0.09
     expressions
    0.09
     solange
    0.08
    Until
    0.08
    until
    0.08
    Activations Density 0.008%

    No Known Activations