© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63368
    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĥļ
    -0.07
    çĪ½åı£
    -0.06
    .cloudflare
    -0.06
    âĢ¦âĢ¦ãĢĤ
    -0.06
    yn
    -0.06
    ide
    -0.06
    /Branch
    -0.06
    raje
    -0.06
    idio
    -0.06
    ipper
    -0.06
    POSITIVE LOGITS
    aire
    0.07
    ç«ŀ
    0.07
    ë¹Ī
    0.07
    fei
    0.07
    lags
    0.07
     awaited
    0.07
    autre
    0.07
    cré
    0.07
    å°±æĺ¯ä¸Ģ个
    0.07
    è¿Ļä¸į
    0.07
    Activations Density 0.000%

    No Known Activations