© 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. 16473
    Prev
    Next
    INDEX
    Explanations

    clinical trial

    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
    ä¸ĢæıIJ
    -0.07
     sublist
    -0.07
    乡åİ¿
    -0.07
    ä¾ĽåºĶ
    -0.07
    upe
    -0.07
    èĤ¥
    -0.06
    é¢ł
    -0.06
     EDUCA
    -0.06
    èĶ¼
    -0.06
     eyed
    -0.06
    POSITIVE LOGITS
    WithPath
    0.08
    èĩªè¯Ħ
    0.07
    èĩªæ£Ģ
    0.07
    incon
    0.07
    è©ķ
    0.07
     ActionType
    0.06
    hus
    0.06
     sustained
    0.06
     Lik
    0.06
    Margins
    0.06
    Activations Density 0.018%

    No Known Activations