© 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. 8351
    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
    ÑĨиÑĤ
    -0.08
     démar
    -0.08
    ä¸Ĭæŀ¶
    -0.08
    angkalan
    -0.08
    ¾¸
    -0.08
    ذاÙĥ
    -0.08
    åĴ¦
    -0.08
     risp
    -0.08
     chôm
    -0.07
    大éĻĨçļĦ
    -0.07
    POSITIVE LOGITS
     imp
    0.06
     paul
    0.06
    åľ¨åİŁ
    0.06
     rem
    0.06
    ALTH
    0.06
    :checked
    0.06
    æ´ŀå¯Ł
    0.06
    оек
    0.06
    ropolis
    0.06
    æĮĩåĩº
    0.06
    Activations Density 0.000%

    No Known Activations