© 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. 22033
    Prev
    Next
    INDEX
    Explanations

    parts of medical or technical terms

    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
    æ
    -0.07
     dyst
    -0.06
     Burton
    -0.06
    身形
    -0.06
    angler
    -0.05
    æĺ¾
    -0.05
    æıIJ
    -0.05
    Nib
    -0.05
    ENSE
    -0.05
    åĸĩ
    -0.05
    POSITIVE LOGITS
    unders
    0.08
    ↵↵    ↵
    0.08
    unde
    0.08
    ExceptionHandler
    0.07
    ä¸įæľį
    0.07
    siz
    0.07
    èµĦæĸĻä¸ĭè½½
    0.07
    å¸ĮæľĽä½łä»¬
    0.07
    olo
    0.07
    )","
    0.07
    Activations Density 0.542%

    No Known Activations