© 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. 7782
    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
    -0.10
     dot
    -0.07
    .dot
    -0.07
    lijk
    -0.06
    è²ī
    -0.06
    å°ĭ
    -0.06
    ÙĦÙĬب
    -0.06
    Terr
    -0.06
    è¿Ľä¸ĢæŃ¥
    -0.06
     nd
    -0.05
    POSITIVE LOGITS
    inig
    0.08
    åĪ«è®©
    0.08
     (*((
    0.07
    åĬłåħ¥æĪij们
    0.07
    ä¿
    0.07
    æľ¬åĽŀçŃĶ
    0.07
    bsites
    0.07
    ç§ijåįı
    0.07
    epat
    0.07
    <dd
    0.07
    Activations Density 0.000%

    No Known Activations