© 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. 1121
    Prev
    Next
    INDEX
    Explanations

    list delimiters

    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
    igni
    -0.07
    ذا
    -0.07
    æıIJä¾ĽåIJĦç§į
    -0.07
    Magn
    -0.06
    .calls
    -0.06
    åĴ«å°º
    -0.06
    abinet
    -0.06
    ider
    -0.06
    onom
    -0.06
    Ñħи
    -0.06
    POSITIVE LOGITS
    esda
    0.08
    odelist
    0.07
    indr
    0.07
    宫é¢Īç³ľçĥĤ
    0.07
    apesh
    0.07
    翼翼
    0.07
     sourceMapping
    0.07
    ragment
    0.07
    ritable
    0.07
    åºĶå½ĵä¾Ŀçħ§
    0.07
    Activations Density 0.030%

    No Known Activations