© 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. 10896
    Prev
    Next
    INDEX
    Explanations

    sucrose or lactose

    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
    ospace
    -0.07
    rey
    -0.07
    .nextElement
    -0.07
    úd
    -0.07
    agnetic
    -0.07
    otion
    -0.07
    [property
    -0.06
    cmc
    -0.06
    lete
    -0.06
    enment
    -0.06
    POSITIVE LOGITS
     sweetness
    0.08
    éħ¶
    0.08
    èĶĹç³ĸ
    0.08
    ç³ĸ
    0.08
    igest
    0.08
    åĪĨ解
    0.07
     sugar
    0.07
     Umg
    0.07
    æľŁçļĦ
    0.07
     malt
    0.07
    Activations Density 0.019%

    No Known Activations