© 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. 8290
    Prev
    Next
    INDEX
    Explanations

    true or false status

    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
    annel
    -0.07
    лаг
    -0.07
    leta
    -0.07
     isra
    -0.06
    è¿ĶåĽŀåĪĹ表
    -0.06
    _separator
    -0.06
    emplacement
    -0.06
    ä½ļ
    -0.06
     اÙĦØŃجÙħ
    -0.06
    xcf
    -0.06
    POSITIVE LOGITS
     falsehood
    0.09
     truth
    0.09
    truth
    0.08
    /false
    0.08
    Truth
    0.08
     status
    0.07
     Truth
    0.07
    åĢ¼
    0.07
     fals
    0.07
     truths
    0.07
    Activations Density 0.006%

    No Known Activations