© 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. 58957
    Prev
    Next
    INDEX
    Explanations

    time and units

    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
    afia
    -0.07
    itone
    -0.07
    ought
    -0.07
    auge
    -0.07
     variant
    -0.07
    ibi
    -0.06
    kee
    -0.06
     Occup
    -0.06
    ava
    -0.06
    åĬ²
    -0.06
    POSITIVE LOGITS
    ä¸ĭä¸Ģ级
    0.09
    äºĮ级
    0.09
    æĿŀ
    0.08
    ÙĪارÙĩ
    0.08
    ä¸Ģ级
    0.07
    _SMS
    0.07
    ensual
    0.07
    inally
    0.07
    UBL
    0.07
    ç¹°
    0.07
    Activations Density 0.169%

    No Known Activations