© 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. 52081
    Prev
    Next
    INDEX
    Explanations

    excerpt, from, content, quoted, simplified

    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
    æĸĩåĵ²
    -0.08
    ÙĪÙĨÙĩ
    -0.07
    妥
    -0.07
    æł¹æľ¬
    -0.07
    ä¸į妥
    -0.07
    izr
    -0.07
    æł¹æľ¬å°±
    -0.07
    人æĪĸ
    -0.07
    ÏĨή
    -0.07
    å¤ļä¹Ī
    -0.07
    POSITIVE LOGITS
    excerpt
    0.07
    пеÑĢе
    0.07
    agger
    0.07
    æѤå¤Ħ
    0.07
    plist
    0.07
    åĭĺ
    0.06
    é»Ħæµ·
    0.06
    valg
    0.06
    istra
    0.06
    enso
    0.06
    Activations Density 0.014%

    No Known Activations