© 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. 47076
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving variables

    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
    specs
    -0.08
    plica
    -0.07
     spec
    -0.07
    ëŀ
    -0.06
     eligible
    -0.06
    转载请注æĺİ
    -0.06
    spec
    -0.06
     specs
    -0.06
    ventura
    -0.06
    Pro
    -0.06
    POSITIVE LOGITS
    ¿
    0.08
    .Bind
    0.07
    iertel
    0.07
    ooks
    0.07
    BOSE
    0.07
    ابة
    0.07
    عت
    0.07
    èķī
    0.07
    zman
    0.07
    cher
    0.07
    Activations Density 0.008%

    No Known Activations