© 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. 4587
    Prev
    Next
    INDEX
    Explanations

    equilateral triangle, lengths, sides

    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
     getro
    -0.08
    ucia
    -0.07
    åĨ·æ¸ħ
    -0.07
    wart
    -0.07
    indet
    -0.07
    ToStr
    -0.07
    mented
    -0.07
    pros
    -0.07
    stral
    -0.07
    ucene
    -0.07
    POSITIVE LOGITS
     triangle
    0.10
     distances
    0.10
     Triangle
    0.10
     triang
    0.09
    Triangle
    0.08
    triangle
    0.08
     lengths
    0.08
    ä¸īè§Ĵå½¢
    0.08
     tensions
    0.08
     triangular
    0.08
    Activations Density 0.002%

    No Known Activations