© 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. 56689
    Prev
    Next
    INDEX
    Explanations

    brand identity, experience, equity, awareness

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    endra
    -0.09
     vá»Ŀi
    -0.08
    chnik
    -0.08
    falls
    -0.07
    cheon
    -0.07
    俱ä¹IJéĥ¨
    -0.07
    -même
    -0.07
    glieder
    -0.07
    ary
    -0.07
    ÑģÑı
    -0.07
    POSITIVE LOGITS
    -name
    0.08
    åı·çļĦ
    0.08
    vila
    0.08
    åIJįçļĦ
    0.07
     spanking
    0.07
    enburg
    0.07
     name
    0.07
    itional
    0.07
    name
    0.07
    _name
    0.07
    Activations Density 0.028%

    No Known Activations