© 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. 44606
    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
    ross
    -0.08
    enska
    -0.08
    icides
    -0.08
    inga
    -0.08
    lais
    -0.07
    atici
    -0.07
    ever
    -0.07
    åĨĽåĮº
    -0.07
    rices
    -0.07
    icap
    -0.07
    POSITIVE LOGITS
    umo
    0.07
    ivial
    0.07
    ully
    0.07
    åĵī
    0.07
    udel
    0.07
    _strlen
    0.07
    MLS
    0.07
    æ¸Ĭ
    0.06
    .arc
    0.06
    StrictEqual
    0.06
    Activations Density 0.000%

    No Known Activations