© 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. 50444
    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
    ught
    -0.08
    cname
    -0.08
    iento
    -0.08
    .Requires
    -0.08
     remit
    -0.07
    ensible
    -0.07
    ebook
    -0.07
    HING
    -0.07
    çļĦä»»ä½ķ
    -0.07
    reshold
    -0.07
    POSITIVE LOGITS
    lander
    0.07
    æ®ĭéħ·
    0.06
    алÑĮнÑĭÑħ
    0.06
    æħĭ
    0.06
    年建
    0.06
    yj
    0.06
    èĢĥçĶŁçļĦ
    0.06
    zott
    0.06
    ä¹Łä¸įå¤ļ
    0.06
    éĵ¶è¡ĮçļĦ
    0.06
    Activations Density 0.000%

    No Known Activations