© 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. 16230
    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
    ä¹ĭå¤ĸçļĦ
    -0.08
    _literals
    -0.07
     rig
    -0.07
     Downing
    -0.07
    jest
    -0.06
    Ïĩο
    -0.06
    人æ°ij代表大ä¼ļ常åĬ¡å§Ķåijĺä¼ļ
    -0.06
    ered
    -0.06
    ering
    -0.06
    _consts
    -0.06
    POSITIVE LOGITS
    inkan
    0.08
    dÃŃ
    0.07
    å¡ŀå°Ķ
    0.07
    olda
    0.07
    odb
    0.07
    å½±éŁ³
    0.07
     ÙħØŃÙĦ
    0.07
    zam
    0.07
    èIJ±
    0.07
    èµ
    0.07
    Activations Density 0.000%

    No Known Activations