© 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. 63335
    Prev
    Next
    INDEX
    Explanations

    inserting or adding at an index

    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
    ennem
    -0.07
    ataka
    -0.07
    èµĦæĸĻä¸ĭè½½
    -0.07
    çĽĹè´¼
    -0.07
    æľĢåIJİä¸Ģ页
    -0.07
    emn
    -0.07
    acor
    -0.07
    交æµģå¹³åı°
    -0.07
     eventName
    -0.07
    æĢ»ç½²
    -0.07
    POSITIVE LOGITS
    æıĴåħ¥
    0.16
     insertion
    0.16
     Insert
    0.14
    Inserted
    0.14
    insert
    0.14
    Insert
    0.14
     inserting
    0.14
    .insert
    0.13
     insert
    0.13
    -insert
    0.13
    Activations Density 0.039%

    No Known Activations