© 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. 49868
    Prev
    Next
    INDEX
    Explanations

    domains and their related contexts

    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
    alz
    -0.06
    æĢ§åıĬ
    -0.06
    æݪ置
    -0.06
    auta
    -0.06
    æݨ移
    -0.06
    regierung
    -0.06
    æĢ§åĴĮ
    -0.06
    arl
    -0.05
    verfahren
    -0.05
    -0.05
    POSITIVE LOGITS
    rawy
    0.09
    cape
    0.09
    å±Ģéķ¿
    0.09
    åĴĮæĶ¿æ²»
    0.09
    å¤Ħ女
    0.09
    aptcha
    0.08
    agos
    0.08
    æĪŁ
    0.08
    odaw
    0.08
    iaus
    0.08
    Activations Density 0.544%

    No Known Activations