© 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. 49858
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and abstractions

    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
    æħ¢è¡Į
    -0.07
     ascend
    -0.07
     ascending
    -0.07
    reff
    -0.07
    StateMachine
    -0.07
    oven
    -0.07
    éłĵ
    -0.07
    ä¸įé½IJ
    -0.07
     underway
    -0.06
     contiguous
    -0.06
    POSITIVE LOGITS
     Lips
    0.07
    ensee
    0.07
    agas
    0.07
    ernel
    0.07
     professionalism
    0.07
     Maxwell
    0.07
    ä½IJ
    0.07
    éĩĩ
    0.07
    .kernel
    0.07
    quire
    0.06
    Activations Density 0.008%

    No Known Activations