© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29827
    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
    ouro
    -0.07
    å½¹
    -0.07
    ngx
    -0.07
    วà¸Ķ
    -0.07
    ORT
    -0.07
    ogado
    -0.06
    åĮĢ
    -0.06
    ril
    -0.06
    OMEM
    -0.06
    èĦ¸çļĦ
    -0.06
    POSITIVE LOGITS
    çļĦ人工
    0.08
    åĥı个
    0.07
    æ³½
    0.07
    ement
    0.07
    dee
    0.07
    ä¸įçĶ¨æĭħå¿ĥ
    0.07
    ä¸į注æĦı
    0.07
    èµ°åĩº
    0.07
    çĶ»çĶ»
    0.07
    ament
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.