© 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. 20587
    Prev
    Next
    INDEX
    Explanations

    informed decisions and choices

    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
    rical
    -0.08
    olini
    -0.08
    ompiler
    -0.08
    rimon
    -0.07
    estions
    -0.07
    fication
    -0.07
     بÙĨدÛĮ
    -0.07
    UFFIX
    -0.07
    Ĺ
    -0.07
    éķ¿æĮīäºĮç»´çłģ
    -0.07
    POSITIVE LOGITS
    edly
    0.08
     ÙĪاÙĦÙħت
    0.08
    елÑĮ
    0.08
    erso
    0.08
     جدÙĭا
    0.07
    /dis
    0.07
    ån
    0.07
    ément
    0.07
    asikan
    0.07
    èµ·è§ģ
    0.07
    Activations Density 0.015%

    No Known Activations