© 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. 59825
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Ant
    -0.07
    ello
    -0.07
    oke
    -0.07
    çľĭçĤ¹
    -0.07
    atto
    -0.07
    åĩ«
    -0.07
    boy
    -0.06
    æĥŃ
    -0.06
    建设æĬķèµĦ
    -0.06
    .au
    -0.06
    POSITIVE LOGITS
    ìĿij
    0.08
     Merrill
    0.07
    mut
    0.07
    ysten
    0.07
    aglio
    0.07
    endorf
    0.07
    趣
    0.07
    ultip
    0.07
    çĽ¾
    0.06
    imes
    0.06
    Activations Density 0.000%

    No Known Activations