© 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. 19612
    Prev
    Next
    INDEX
    Explanations

    prime number checks

    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
     ↵
    -0.07
    oran
    -0.06
     ↵            ↵
    -0.06
    {
    -0.06
    ich
    -0.06
    ram
    -0.06
     Rauch
    -0.05
     Cricket
    -0.05
    å·¥
    -0.05
    -0.05
    POSITIVE LOGITS
    izont
    0.09
    è®´
    0.08
    éĺħ读åħ¨æĸĩ
    0.08
    weiler
    0.08
    itarra
    0.08
    ableView
    0.08
    ppard
    0.08
    天éªĦ
    0.08
    ãĥ¼ãĥĹ
    0.08
    icola
    0.08
    Activations Density 0.005%

    No Known Activations