© 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. 34017
    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
    ultas
    -0.08
    ĻĤ
    -0.08
    rige
    -0.08
    ç½ijåıĭè¯Ħ论
    -0.08
    rest
    -0.07
    ultos
    -0.07
    جة
    -0.07
    rox
    -0.07
    æĹłéĤª
    -0.07
    çĥĤ
    -0.07
    POSITIVE LOGITS
    åı°æµ·
    0.07
    fds
    0.07
     favourites
    0.07
    æľŁå¾ħ
    0.07
    帳
    0.06
    ovah
    0.06
    ä¸īæĹ¥
    0.06
    ائÙĩا
    0.06
    vars
    0.06
     Feedback
    0.06
    Activations Density 0.000%

    No Known Activations