© 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. 12990
    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
    бÑĢ
    -0.08
    cef
    -0.08
    -report
    -0.07
    عÙĪ
    -0.07
     opd
    -0.07
    acce
    -0.07
    ±
    -0.07
    åıij表讨论
    -0.07
    _reporting
    -0.07
    IData
    -0.07
    POSITIVE LOGITS
    piel
    0.07
    åĽ¾è§£
    0.07
    æľĪåŃIJ
    0.06
    поÑĩ
    0.06
    åĨ
    0.06
    alak
    0.06
    ä¸įæľ½
    0.06
    izont
    0.06
    lies
    0.06
    é¦
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.