© 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. 56764
    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
    åĪģ
    -0.06
    egan
    -0.06
    ...
    -0.06
    æĨ
    -0.06
    ench
    -0.06
    owned
    -0.06
    �
    -0.06
    å±ķéĸĭ
    -0.06
    ÂŃt
    -0.06
    igung
    -0.05
    POSITIVE LOGITS
    ondre
    0.08
    urgo
    0.08
    ayne
    0.08
    _ips
    0.08
     %@
    0.07
    loch
    0.07
    åѦæĬ¥
    0.07
    èµĦæºIJç½ij
    0.07
    uild
    0.07
    rops
    0.07
    Activations Density 0.000%

    No Known Activations