© 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. 37719
    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
    ä¸įæ¸Ŀ
    -0.09
    gaard
    -0.08
    <|box_end|>
    -0.08
    ä¸įèĩ³
    -0.07
    ignum
    -0.07
    árd
    -0.07
    barang
    -0.07
    ILITY
    -0.07
    gege
    -0.07
    kest
    -0.07
    POSITIVE LOGITS
    主
    0.08
     main
    0.07
    oler
    0.06
    åĮħ饺åŃIJ
    0.06
    Pa
    0.06
    å¿ĥçĶ°
    0.06
    红é¢Ĩå·¾
    0.06
    vn
    0.06
     outlining
    0.06
    _unsigned
    0.06
    Activations Density 0.000%

    No Known Activations