© 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. 596
    Prev
    Next
    INDEX
    Explanations

    angle

    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
    å¦ĤæŀľçľŁçļĦ
    -0.07
    igas
    -0.06
    fy
    -0.06
    ffffffff
    -0.06
    为çĪ±
    -0.06
     history
    -0.06
    éļĻ
    -0.06
    åįķ个
    -0.06
    ctest
    -0.06
     History
    -0.06
    POSITIVE LOGITS
     angles
    0.10
     angle
    0.10
    angle
    0.09
    -angle
    0.09
    è§Ĵ度
    0.09
     Angle
    0.09
    Angle
    0.08
    è§Ĵ
    0.08
    诱
    0.08
     Ñĥгол
    0.08
    Activations Density 0.002%

    No Known Activations