© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12241
    Prev
    Next
    INDEX
    Explanations

    advances in technology

    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
    _UNUSED
    -0.08
    èĩªæķij
    -0.07
    yder
    -0.07
     подлежа
    -0.07
     unsuccessfully
    -0.07
    è¡Įæĸĩ
    -0.06
    fahr
    -0.06
    çIJµçIJ¶
    -0.06
    lassian
    -0.06
    举ä¸Ģåıįä¸ī
    -0.06
    POSITIVE LOGITS
    æĬĢæľ¯çļĦåıijå±ķ
    0.10
     technologies
    0.10
     enabling
    0.10
    使å¾Ĺ
    0.10
     technology
    0.10
    çļĦä»Ĭ天
    0.10
     techniques
    0.10
     advances
    0.10
     enables
    0.09
     advancements
    0.09
    Activations Density 0.613%

    No Known Activations