© 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. 21922
    Prev
    Next
    INDEX
    Explanations

    parenthesized expressions or equations

    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
    æĶ¯
    -0.08
    agn
    -0.07
    èį
    -0.06
    âĢ¦
    -0.06
    éĺ³åħī
    -0.06
    äºļ
    -0.06
    缴åĪ°
    -0.06
    åIJİ天
    -0.06
    jin
    -0.06
     quad
    -0.06
    POSITIVE LOGITS
    梦æĥ³çļĦ
    0.08
    æŶ任
    0.08
    éªĭ
    0.08
    gage
    0.08
    hots
    0.08
    WISE
    0.08
    å°ı家
    0.08
    (KP
    0.08
    lify
    0.08
    åĴĮåIJĮäºĭ
    0.08
    Activations Density 0.001%

    No Known Activations