© 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. 55438
    Prev
    Next
    INDEX
    Explanations

    mathematical and symbolic expressions

    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
    angg
    -0.10
    ingen
    -0.08
    çī¹æľĹ
    -0.08
    wm
    -0.07
    angu
    -0.07
    çī¹åĭĴ
    -0.07
    cpf
    -0.07
    ستر
    -0.07
    oyer
    -0.07
    ãĥĥãĤŃ
    -0.07
    POSITIVE LOGITS
    æ´ŀ
    0.06
    unas
    0.06
    Inflater
    0.06
     pret
    0.06
    ((-
    0.06
    äºĭ项
    0.06
    arat
    0.06
    aks
    0.06
     is
    0.06
    irth
    0.06
    Activations Density 0.043%

    No Known Activations