© 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. 21909
    Prev
    Next
    INDEX
    Explanations

    apply regular

    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
    çĶ¸
    -0.07
     mily
    -0.07
    秣åĶ®
    -0.06
     ratus
    -0.06
    ivid
    -0.06
    ẳng
    -0.06
    åĭīåĬ±
    -0.06
    è¡Ĩ
    -0.06
    -0.06
     plac
    -0.06
    POSITIVE LOGITS
    åľ¨æīĢ
    0.08
    aising
    0.08
    并ä¸į代表
    0.07
     proxies
    0.07
    çĶ¨è¡ĮåĬ¨
    0.07
     بÙħعÙĨÙī
    0.07
    å®ľäºº
    0.07
    asure
    0.07
    ä¸į代表
    0.07
    opping
    0.07
    Activations Density 0.145%

    No Known Activations