© 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. 55615
    Prev
    Next
    INDEX
    Explanations

    existence of

    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
    OMIC
    -0.08
     rever
    -0.08
    raud
    -0.07
    emean
    -0.07
     измеÑĢениÑı
    -0.07
    误ä¼ļ
    -0.07
    åĪĨæĺİ
    -0.07
    remen
    -0.07
    èѦæĪĴ
    -0.07
    <typeof
    -0.07
    POSITIVE LOGITS
     guaranteed
    0.12
     guarantee
    0.11
     guarantees
    0.11
    ä¿Ŀè¯ģ
    0.10
    ä¿Ŀè¯ģäºĨ
    0.10
     Guaranteed
    0.09
     garant
    0.09
     garanti
    0.09
     Guarantee
    0.09
     garantia
    0.09
    Activations Density 0.043%

    No Known Activations