© 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. 51755
    Prev
    Next
    INDEX
    Explanations

    the average, geopolitical, fertile, events, license

    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
     and
    -0.07
     similar
    -0.06
     ahead
    -0.06
    nem
    -0.06
     versus
    -0.06
     with
    -0.06
     throughout
    -0.06
     today
    -0.06
     permanente
    -0.06
    ,
    -0.06
    POSITIVE LOGITS
    ses
    0.18
     latter
    0.17
     aforementioned
    0.16
     same
    0.15
     entire
    0.13
    oretical
    0.12
     entirety
    0.12
     simplest
    0.12
    ore
    0.11
     usual
    0.11
    Activations Density 3.370%

    No Known Activations