© 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. 29258
    Prev
    Next
    INDEX
    Explanations

    html/code tags and strings

    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
    é¥®é£Łä¸Ĭ
    -0.07
    oth
    -0.07
     thr
    -0.07
    }_${
    -0.07
     deepest
    -0.07
    خر
    -0.06
    `\
    -0.06
    æĹłæīĢè°ĵ
    -0.06
     }//
    -0.06
    sten
    -0.06
    POSITIVE LOGITS
    ástica
    0.07
    åĨħèĥĨ
    0.07
    å°¤åħ¶
    0.07
     Pull
    0.07
    unya
    0.07
    anean
    0.07
    inheiten
    0.07
    -js
    0.07
    天åĴĮ
    0.07
    èĻ¹
    0.06
    Activations Density 0.011%

    No Known Activations