© 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. 48981
    Prev
    Next
    INDEX
    Explanations

    Importer, export, import, search, Undo

    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
    UnderTest
    -0.07
    bacher
    -0.07
    enta
    -0.07
    گاÙĨ
    -0.07
    Decorator
    -0.07
    olum
    -0.07
    ensen
    -0.07
    æĵ¦äº®
    -0.06
    nes
    -0.06
     ris
    -0.06
    POSITIVE LOGITS
    mgr
    0.08
    able
    0.08
    ãĥĥãĤŃãĥ³ãĤ°
    0.07
    edor
    0.07
    gable
    0.07
    emann
    0.07
    ousse
    0.07
    _helper
    0.07
    еди
    0.07
     destinations
    0.07
    Activations Density 0.286%

    No Known Activations