© 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. 29403
    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
    æ´»çļĦ
    -0.07
    ãģ¾ãģ¾
    -0.07
    çĤ¹åŃIJ
    -0.07
    lest
    -0.07
    aked
    -0.07
    atcher
    -0.07
    åĦ¿çļĦ
    -0.07
    czy
    -0.07
    clo
    -0.06
    åĨĮ
    -0.06
    POSITIVE LOGITS
    eves
    0.08
     Offensive
    0.07
    andan
    0.07
     hÃł
    0.07
    orman
    0.07
    .dumps
    0.07
    ponsible
    0.07
    lás
    0.07
    çĽİ
    0.07
    èį¼
    0.07
    Activations Density 0.000%

    No Known Activations