© 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. 11623
    Prev
    Next
    INDEX
    Explanations

    elliptic curve, Wales, hypercholesterolemia

    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
    éĻIJ度çļĦ
    -0.07
     Aufenthalts
    -0.06
     Luck
    -0.06
     Arbor
    -0.06
     seber
    -0.06
     khoang
    -0.06
     straf
    -0.06
    ç©¿éĢı
    -0.06
    opo
    -0.06
    ı
    -0.06
    POSITIVE LOGITS
    eteur
    0.09
     triples
    0.08
     scaled
    0.08
    etz
    0.07
    -scal
    0.07
    Reuse
    0.07
     autogenerated
    0.07
    缩æĶ¾
    0.07
    serter
    0.07
    ä¸īèģĶ
    0.07
    Activations Density 0.002%

    No Known Activations