© 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. 26809
    Prev
    Next
    INDEX
    Explanations

    "this is" followed by description

    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
    uhl
    -0.08
    è¿Ļ个è¯į
    -0.08
    ä¿¡æģ¯ä»ħä¾ĽåıĤèĢĥ
    -0.08
    æīĢéľĢçļĦ
    -0.08
    ç³ĸå°¿
    -0.07
    asso
    -0.07
    交æĺĵé¢Ŀ
    -0.07
    æľĢæĸ°æĽ´æĸ°
    -0.07
    /welcome
    -0.07
    rchive
    -0.07
    POSITIVE LOGITS
     primarily
    0.08
     reminiscent
    0.07
     recurring
    0.07
     essentially
    0.07
    é¦ĸæ¬¡åľ¨
    0.06
     part
    0.06
     largely
    0.06
    å¿ĥçļĦ
    0.06
     therefore
    0.06
     dealing
    0.06
    Activations Density 0.023%

    No Known Activations