© 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. 42555
    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
    çķ´
    -0.07
    _CPU
    -0.07
    blatt
    -0.07
    .af
    -0.06
    ĩ
    -0.06
    WidgetItem
    -0.06
    ouvel
    -0.06
     characterization
    -0.06
    ovre
    -0.06
    [[
    -0.06
    POSITIVE LOGITS
    ç½ĹéĤ£
    0.07
    çĴĢ
    0.07
    èIJ½èIJ½
    0.07
    ingas
    0.07
    fy
    0.07
     emer
    0.07
    iaga
    0.07
    ìĥģìĿĢ
    0.07
    VOID
    0.07
    æĤ¶
    0.07
    Activations Density 0.000%

    No Known Activations