© 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. 57776
    Prev
    Next
    INDEX
    Explanations

    database write operations

    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
    ëij¥
    -0.07
     spect
    -0.07
    elis
    -0.07
    licant
    -0.07
    åĩºä¾Ĩ
    -0.07
    esel
    -0.07
    åĩºæĿ¥
    -0.07
    åĩºæĿ¥äºĨ
    -0.07
    arium
    -0.07
    åĪĨåĩº
    -0.07
    POSITIVE LOGITS
     insertion
    0.10
    (insert
    0.10
    lobber
    0.10
     insert
    0.10
     inser
    0.09
    OrUpdate
    0.09
    æıĴåħ¥
    0.09
    insert
    0.09
    åĨĻåħ¥
    0.09
     Insert
    0.09
    Activations Density 0.514%

    No Known Activations