© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 56968
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts followed by related terms

    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
    öff
    -0.09
    çıĪ
    -0.09
    ogo
    -0.08
    champ
    -0.08
    ä¹ĭæĢ¥
    -0.08
    leftright
    -0.08
    жо
    -0.08
    гелÑĮ
    -0.08
    plats
    -0.08
    кÑĥл
    -0.08
    POSITIVE LOGITS
    -ish
    0.10
    ness
    0.08
    /non
    0.08
    -looking
    0.08
    ity
    0.07
    erci
    0.07
    ä¸Ķæľī
    0.07
     albeit
    0.06
    项
    0.06
    ijk
    0.06
    Activations Density 0.120%

    No Known Activations