© 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. 50024
    Prev
    Next
    INDEX
    Explanations

    definition of 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
    æİ©
    -0.07
    deaux
    -0.07
    megen
    -0.07
    迹
    -0.07
    èĦĤ
    -0.06
    å¦Ĥ对
    -0.06
     Maio
    -0.06
    éħĹ
    -0.06
    çı
    -0.06
    enius
    -0.06
    POSITIVE LOGITS
    izan
    0.07
    æµı
    0.07
    oto
    0.07
    åĶ¯ä¸Ģä¸Ģ个
    0.07
    µ¬
    0.07
    -messages
    0.07
     ë°Ķë¡ľ
    0.07
     combinations
    0.07
    تÙĩ
    0.07
    /Library
    0.06
    Activations Density 0.004%

    No Known Activations