© 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. 29797
    Prev
    Next
    INDEX
    Explanations

    Hind III restriction enzyme

    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
    åħ»æ´»
    -0.07
    æľªç»ı
    -0.07
     ident
    -0.07
    缴çļĦ
    -0.07
    eté
    -0.06
    æľªè¢«
    -0.06
    æ²³éķĩ
    -0.06
    ings
    -0.06
    éģĵè·¯ä¸Ĭ
    -0.06
     identical
    -0.06
    POSITIVE LOGITS
    å®ľäºº
    0.08
    ablanca
    0.08
    黼
    0.08
    -cli
    0.07
    ziÄĻ
    0.07
    clr
    0.07
    isoft
    0.07
    åĴĮ西
    0.07
    Clr
    0.07
    æĪijçļĦä¼ģä¸ļ
    0.07
    Activations Density 0.015%

    No Known Activations