© 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. 14945
    Prev
    Next
    INDEX
    Explanations

    protonated

    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
    -0.08
    mite
    -0.07
    örper
    -0.07
    宫éĩĮ
    -0.07
    ihad
    -0.06
    èŀĤ
    -0.06
    opal
    -0.06
    身ä½ĵç´łè´¨
    -0.06
    çĶŁç´ł
    -0.06
    ศาสà¸ķรà¹Į
    -0.06
    POSITIVE LOGITS
    ÙĬÙĦÙĩ
    0.07
    å¤Ħåľ¨
    0.07
     incoming
    0.07
    /ion
    0.07
     McGr
    0.07
    elli
    0.07
    欢è¿İåħī临
    0.07
    ogat
    0.07
    äºĨæķ´ä¸ª
    0.07
    ached
    0.07
    Activations Density 0.001%

    No Known Activations