© 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. 16004
    Prev
    Next
    INDEX
    Explanations

    email addresses, research papers, programming terms

    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
    ä¸įåı¯æĢĿè®®
    -0.09
    ities
    -0.08
    ر
    -0.08
    ×ķ׼׾
    -0.08
    ighting
    -0.07
    thinkable
    -0.07
    ÃŃf
    -0.07
    vey
    -0.07
    èĢĮä¸Ķè¦ģ
    -0.07
    ä½łåij¢
    -0.07
    POSITIVE LOGITS
    Ø©
    0.10
    ¹
    0.09
    edException
    0.09
    Äįka
    0.08
    AsStream
    0.08
    enstein
    0.08
    esda
    0.08
    CharCode
    0.08
    /Getty
    0.07
    edList
    0.07
    Activations Density 0.008%

    No Known Activations