© 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. 8882
    Prev
    Next
    INDEX
    Explanations

    alcohol, drinking, drunk, wine

    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
    гне
    -0.08
    åįĪé¤IJ
    -0.07
    èįł
    -0.07
    éĺ´å½±
    -0.07
     airl
    -0.07
    aira
    -0.07
     electrom
    -0.07
    交çĶµ
    -0.07
     Gmail
    -0.07
    ynchronous
    -0.06
    POSITIVE LOGITS
    éħĴ
    0.18
     alcohol
    0.17
    éħĴç²¾
    0.17
    éħĴçļĦ
    0.16
     Alcohol
    0.16
    çļĦéħĴ
    0.16
    éħĴåIJİ
    0.16
    çĻ½éħĴ
    0.15
     alkoh
    0.15
     alcoholic
    0.15
    Activations Density 0.220%

    No Known Activations