© 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. 25456
    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
    ibil
    -0.08
    øk
    -0.07
    ยà¹Īา
    -0.07
    ettings
    -0.07
    rières
    -0.07
    _No
    -0.07
    él
    -0.07
    è±Ĩçĵ£
    -0.06
     hab
    -0.06
    ëįĶëĿ¼ê³łìļĶ
    -0.06
    POSITIVE LOGITS
    pires
    0.08
    onsor
    0.08
    Ø©
    0.07
    oses
    0.07
    ogy
    0.07
    ׳×Ŀ
    0.07
    èij
    0.07
    æ¹¾
    0.07
    äºĨå¤ļå°ij
    0.07
    maar
    0.07
    Activations Density 0.000%

    No Known Activations