© 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. 46254
    Prev
    Next
    INDEX
    Explanations

    safety systems and concerns

    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
    æł·çļĦ
    -0.08
    ä¾ĨçļĦ
    -0.07
    ensed
    -0.07
    ä¸įä¼ij
    -0.07
    ιά
    -0.07
    ather
    -0.07
    aldi
    -0.07
    bildungs
    -0.07
    .nih
    -0.07
    خاÙĨÙĩ
    -0.07
    POSITIVE LOGITS
    yer
    0.09
    eguard
    0.09
    /security
    0.08
    èµ·è§ģ
    0.08
    -minded
    0.08
    fully
    0.08
    eux
    0.08
    æĢ§çļĦ
    0.08
    pherd
    0.08
    ìĤ¬ê³ł
    0.08
    Activations Density 0.017%

    No Known Activations