© 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. 33648
    Prev
    Next
    INDEX
    Explanations

    field, cumsum, order, majority, special issue

    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
    asca
    -0.08
    åĴĮæĢĿèĢĥ
    -0.08
    hoven
    -0.08
    ITIES
    -0.07
    erings
    -0.07
    armo
    -0.07
    äºĶèĬ±åħ«
    -0.07
     statis
    -0.07
    PageIndex
    -0.07
    ä¹Łå¾Īæľī
    -0.07
    POSITIVE LOGITS
    âĢIJ
    0.08
    âĢij
    0.07
    (?)
    0.07
    è·Łåīį
    0.07
    åĵī
    0.06
    大æ³ķ
    0.06
    tect
    0.06
    ipy
    0.06
    ":{"
    0.06
                                 ↵
    0.06
    Activations Density 0.013%

    No Known Activations