© 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. 31470
    Prev
    Next
    INDEX
    Explanations

    ontological, metaphysical, existential

    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
    lew
    -0.09
    edException
    -0.09
    ystone
    -0.08
     halinde
    -0.08
    天éªĦ
    -0.08
    ائÙĥ
    -0.08
    ulo
    -0.08
    ObjectContext
    -0.08
    _fore
    -0.08
    FromClass
    -0.08
    POSITIVE LOGITS
    æĦıä¹īä¸ĬçļĦ
    0.08
    åĴĮæ³ķå¾ĭ
    0.07
    ancer
    0.07
    追éĹ®
    0.07
    itical
    0.07
    ide
    0.07
    èİ«æµĭ
    0.07
    å±ĤéĿ¢çļĦ
    0.07
    æĦıä¹īä¸Ĭ
    0.07
    询
    0.07
    Activations Density 0.004%

    No Known Activations