© 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. 9124
    Prev
    Next
    INDEX
    Explanations

    "Let" ... "let"

    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
    ello
    -0.08
    _wrap
    -0.08
    èĤºèħij
    -0.07
    ä¹ħè¿Ŀ
    -0.07
    èĤª
    -0.07
    åľ¨åŃ¦ä¹łä¸Ń
    -0.07
    stry
    -0.06
    urai
    -0.06
    akra
    -0.06
    UTE
    -0.06
    POSITIVE LOGITS
    åĸ½
    0.07
    gers
    0.07
    çĶŁçļĦ
    0.07
    è¹
    0.06
    èµŀ
    0.06
     getItem
    0.06
    (named
    0.06
    æ¸Ķä¸ļ
    0.06
    æIJŃ
    0.06
     grand
    0.06
    Activations Density 0.004%

    No Known Activations