© 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. 64242
    Prev
    Next
    INDEX
    Explanations

    equivalent or corresponding

    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
    ResourceId
    -0.07
    侥幸
    -0.07
    æĮĩ导åѦçĶŁ
    -0.07
     helst
    -0.07
    æŁIJçĶ²
    -0.07
    好è¿IJ
    -0.07
    æŁIJ个
    -0.07
     narratives
    -0.07
    bü
    -0.06
    ä½Ĩæĺ¯ä¸Ģ
    -0.06
    POSITIVE LOGITS
     equivalent
    0.08
     equivalente
    0.08
    Singleton
    0.08
    对åºĶ
    0.07
    asure
    0.07
    Equivalent
    0.07
    ATUS
    0.07
    @[
    0.07
     surrogate
    0.07
     correspond
    0.07
    Activations Density 0.006%

    No Known Activations