© 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. 46147
    Prev
    Next
    INDEX
    Explanations

    math and counts

    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
    _ud
    -0.07
    zat
    -0.07
    éijij
    -0.07
    ÄįÃŃ
    -0.07
    odia
    -0.06
    ÙĤÙħ
    -0.06
    roda
    -0.06
    èIJ±
    -0.06
     proceeding
    -0.06
    çĶľçĶľçļĦ
    -0.06
    POSITIVE LOGITS
    tras
    0.08
    ardı
    0.08
    åıĤèĢĥä»·æł¼
    0.07
    razia
    0.07
    åĩ«
    0.07
    åIJŀ
    0.07
    ÐĻ
    0.07
    arik
    0.07
    -Y
    0.07
    acia
    0.07
    Activations Density 0.007%

    No Known Activations