© 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. 4857
    Prev
    Next
    INDEX
    Explanations

    ranking and qualitative features

    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
    宿
    -0.09
    ivated
    -0.08
    anker
    -0.08
    iedi
    -0.08
    amis
    -0.08
    论åĿĽä¸Ĭ
    -0.07
    Ïģε
    -0.07
    haps
    -0.07
     Benson
    -0.07
    综åIJĪçĹĩ
    -0.07
    POSITIVE LOGITS
    ä¸įè¦ģ被
    0.08
     Rat
    0.08
    gist
    0.08
     Rig
    0.07
     saja
    0.07
    ä¸į失
    0.07
    è¿ľè¿ij
    0.07
    ä¸įè¦ģåĽłä¸º
    0.07
     Representative
    0.07
    ä¸įå¿ħ
    0.07
    Activations Density 0.042%

    No Known Activations