© 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. 38657
    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
    عÙĪ
    -0.09
    aland
    -0.08
     NotImplemented
    -0.07
    aza
    -0.07
    inyin
    -0.07
    æľ±åħĥ
    -0.07
    aliste
    -0.07
    irl
    -0.07
    ода
    -0.06
    egative
    -0.06
    POSITIVE LOGITS
    vid
    0.07
    _cast
    0.07
    koa
    0.07
    à¹Ģสà¸Ļ
    0.06
    _multip
    0.06
    ucc
    0.06
     Admir
    0.06
    rzy
    0.06
    ä¹Łå¥½
    0.06
    ota
    0.06
    Activations Density 0.000%

    No Known Activations