© 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. 42220
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and elements

    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
    orme
    -0.09
    lessly
    -0.09
    hood
    -0.09
    iette
    -0.08
    most
    -0.08
    اÙĭ
    -0.08
    onti
    -0.08
    ÛĮت
    -0.08
    à¹Ĩ
    -0.08
    éłĵ
    -0.08
    POSITIVE LOGITS
    èĩªå·±
    0.08
    es
    0.08
    Ùĩ
    0.08
    ะ
    0.08
    u
    0.07
    ÙĪ
    0.07
    ê°Ģ
    0.07
    æĺ¯
    0.07
    ç½ķ
    0.07
    Ħ
    0.06
    Activations Density 0.005%

    No Known Activations