© 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. 13507
    Prev
    Next
    INDEX
    Explanations

    he said, he's, his name

    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
    olt
    -0.07
    ersh
    -0.07
    ufe
    -0.07
    Ñij
    -0.07
    illed
    -0.06
    çļĦ第ä¸Ģ天
    -0.06
    unst
    -0.06
    LBL
    -0.06
     tum
    -0.06
    Fcn
    -0.06
    POSITIVE LOGITS
    velt
    0.08
    å¹ħ
    0.08
    ettel
    0.07
    سÙĬÙĦ
    0.07
    æĤ¨åı¯èĥ½
    0.07
     pret
    0.07
    åºĶ该ä¼ļ
    0.07
    ettori
    0.07
    -global
    0.07
    laus
    0.07
    Activations Density 0.192%

    No Known Activations