© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9078
    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
    emor
    -0.07
    pyx
    -0.07
    èĮ¨
    -0.07
    éĥĿ
    -0.06
     Äijinh
    -0.06
     amongst
    -0.06
    æıIJ
    -0.06
    çī¹åĪ«æĺ¯
    -0.06
     Sometimes
    -0.06
    -ish
    -0.06
    POSITIVE LOGITS
    /*@
    0.08
    éķ¿ä¸º
    0.08
    é£Łåĵģåį«çĶŁ
    0.08
    对ä¸Ĭ
    0.07
     alike
    0.07
    гнÑĥ
    0.07
    agerie
    0.07
    OTTO
    0.07
    jde
    0.07
    iany
    0.07
    Activations Density 0.000%

    No Known Activations