© 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. 48135
    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
     parch
    -0.08
    æĶ¶èĹıæľ¬ç«Ļ
    -0.07
    azon
    -0.07
    ียà¸ļ
    -0.07
    ä¸įçķĻ
    -0.07
    quera
    -0.06
    çŀ»
    -0.06
    好æ¯Ķ
    -0.06
    ĻĤ
    -0.06
    æľºçŃī
    -0.06
    POSITIVE LOGITS
    jø
    0.08
    nado
    0.07
    ç¬ij
    0.07
    betes
    0.07
    itado
    0.06
    lug
    0.06
    æĢ»æĪIJ
    0.06
    ught
    0.06
    hack
    0.06
    аÑĤÑĥ
    0.06
    Activations Density 0.000%

    No Known Activations