© 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. 12439
    Prev
    Next
    INDEX
    Explanations

    fax, therapists, workers, escalators, fragment, plugin

    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
    ä¹Łå°±æĺ¯
    -0.09
    forth
    -0.08
    acer
    -0.07
    Äįe
    -0.07
    بØŃ
    -0.07
    ril
    -0.07
     ir
    -0.07
    amu
    -0.06
    æĵ
    -0.06
    临
    -0.06
    POSITIVE LOGITS
    zilla
    0.07
    é¶
    0.07
    mailer
    0.07
    ÙĪØ·
    0.07
    loch
    0.07
    çļĦ强大
    0.06
    á»IJC
    0.06
    uitar
    0.06
    IDS
    0.06
    য়ার
    0.06
    Activations Density 0.296%

    No Known Activations