© 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. 28915
    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
    elim
    -0.08
    漫
    -0.07
    าว
    -0.06
     Unicorn
    -0.06
    abcdefghijkl
    -0.06
    utta
    -0.06
     ${(
    -0.06
     Elim
    -0.06
     Confidential
    -0.06
    ساÙĨ
    -0.06
    POSITIVE LOGITS
    ä»»
    0.07
     profound
    0.07
    cookie
    0.07
    rug
    0.07
    çĽĬçĶŁ
    0.07
    ä»»çĶ¨
    0.06
    пÑĭ
    0.06
    td
    0.06
     ÑĢей
    0.06
    èģĺ
    0.06
    Activations Density 0.000%

    No Known Activations