© 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. 25270
    Prev
    Next
    INDEX
    Explanations

    timestamp and time

    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
    enville
    -0.07
    è¿ĩå¹´çļĦ
    -0.07
     netr
    -0.07
    à¸Ĭะ
    -0.07
    koch
    -0.07
     Laboratories
    -0.07
    ffici
    -0.07
    TOOLS
    -0.07
    _mgr
    -0.07
    ĮĢ
    -0.07
    POSITIVE LOGITS
    legg
    0.06
    ä¸įè§ī
    0.06
    æIJ
    0.06
     stringify
    0.06
    iers
    0.06
    alez
    0.06
    veis
    0.06
     Accessed
    0.06
    berge
    0.06
     unseen
    0.06
    Activations Density 0.102%

    No Known Activations