© 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. 59802
    Prev
    Next
    INDEX
    Explanations

    height-wise

    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
     decat
    -0.07
    åĪ°ä¸ĭ
    -0.07
    aticon
    -0.07
    éĩĮäºļ
    -0.07
    好äºĭ
    -0.07
    Ù°
    -0.07
    æĬµ
    -0.07
    éĽªå³°
    -0.07
    øl
    -0.07
     Shia
    -0.07
    POSITIVE LOGITS
    éĻ¤å¤ĸ
    0.10
    å°¤
    0.07
     paradigm
    0.07
    éĨį
    0.07
     nevertheless
    0.06
    åĺĽ
    0.06
     practise
    0.06
     admittedly
    0.06
     paran
    0.06
     presently
    0.06
    Activations Density 0.713%

    No Known Activations