© 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. 40805
    Prev
    Next
    INDEX
    Explanations

    solve for equations

    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
    å½Ī
    -0.07
    anean
    -0.07
    éĢģä¸Ģ
    -0.07
    sbin
    -0.06
    vet
    -0.06
    å°ijäºİ
    -0.06
    consts
    -0.06
    趣
    -0.06
    ervals
    -0.06
    æľīå¾Ī好çļĦ
    -0.06
    POSITIVE LOGITS
    åħ¬å¼ı
    0.08
    ä½łåij¢
    0.08
    æĶĺ
    0.08
    ectu
    0.08
     Rear
    0.08
     ricav
    0.07
     rearr
    0.07
     formula
    0.07
    æĶ¹åĨĻ
    0.07
    以å¤ĩ
    0.07
    Activations Density 0.008%

    No Known Activations