© 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. 27064
    Prev
    Next
    INDEX
    Explanations

    outdoor or indoor locations

    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
    Ĺ
    -0.08
    alist
    -0.08
    uate
    -0.07
    chet
    -0.07
    à§Ģয়
    -0.07
    eder
    -0.07
    naires
    -0.07
     Ñģобой
    -0.07
    OfDay
    -0.07
    Ïģαι
    -0.07
    POSITIVE LOGITS
    entifier
    0.09
    zul
    0.08
    eref
    0.08
    imensional
    0.08
    /out
    0.08
    idad
    0.08
    abouts
    0.08
    izar
    0.08
    erness
    0.08
    chemy
    0.08
    Activations Density 0.136%

    No Known Activations