© 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. 18809
    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
    åı²
    -0.07
    åĽ½æŃĮ
    -0.07
    apolis
    -0.07
    nado
    -0.07
    /logo
    -0.07
    çıĬ
    -0.07
    -ajax
    -0.07
    æĶ¿
    -0.07
    /apps
    -0.06
    affen
    -0.06
    POSITIVE LOGITS
    DAT
    0.08
    å¾ĹéĿŀ常
    0.08
    èĮ¹
    0.07
    بÙĤ
    0.07
     Legislat
    0.07
        ↵↵↵
    0.07
    ller
    0.07
    对çĶŁæ´»
    0.07
     Aval
    0.07
    Äįia
    0.07
    Activations Density 0.000%

    No Known Activations