© 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. 56744
    Prev
    Next
    INDEX
    Explanations

    implicit or explicit usage

    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
    orma
    -0.08
    ä¸ĢæĶ¹
    -0.07
    gor
    -0.07
     Sung
    -0.06
    å½»åºķ
    -0.06
    åĪ¹
    -0.06
    èģļ
    -0.06
     prist
    -0.06
    é¢
    -0.06
     Belt
    -0.06
    POSITIVE LOGITS
    å¾®ä¸į足
    0.08
    æĸ¹ä¾¿çļĦ
    0.08
    OnError
    0.08
    缸çľĭ
    0.08
    enez
    0.08
    enang
    0.08
    andung
    0.07
     implicitly
    0.07
    ัà¹Īà¸Ļ
    0.07
     Implicit
    0.07
    Activations Density 0.005%

    No Known Activations