© 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. 28887
    Prev
    Next
    INDEX
    Explanations

    position update and control

    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
    活水
    -0.07
    æ´Ľä¼Ĭ
    -0.07
    åĶ§
    -0.06
    جاÙĨ
    -0.06
    åij¼åij¼
    -0.06
     Sheridan
    -0.06
    ä¸İåĽ½åĨħ
    -0.06
    ยà¹Īà¸Ńย
    -0.06
    èĩĢ
    -0.06
     digest
    -0.06
    POSITIVE LOGITS
    åĴĮå·¥ä½ľ
    0.08
    Serialize
    0.08
     displ
    0.08
    ä¾Ŀæ³ķèĩªä¸»
    0.07
    èĭ±æĸĩåIJįåŃĹ
    0.07
    åĴĮæĬĢèĥ½
    0.07
    .alias
    0.07
    ucus
    0.07
    ä½į移
    0.07
    .charCodeAt
    0.07
    Activations Density 0.008%

    No Known Activations