© 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. 44802
    Prev
    Next
    INDEX
    Explanations

    topological sorting and causal relationships

    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
    æ¹Ľ
    -0.09
    abwe
    -0.08
    _border
    -0.07
    ibold
    -0.07
    ocr
    -0.07
    akwa
    -0.07
    auss
    -0.07
    ãĤ¬ãĥ¼ãĥī
    -0.07
     uzu
    -0.07
    BorderStyle
    -0.07
    POSITIVE LOGITS
    Hier
    0.10
    å±Ĥ级
    0.10
     causal
    0.10
     hierarchical
    0.09
    å±Ĥ次
    0.09
    åĽłæŀľ
    0.09
     caus
    0.08
    æİĴåºı
    0.08
     hier
    0.08
     ordering
    0.08
    Activations Density 0.024%

    No Known Activations