© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12000
    Prev
    Next
    INDEX
    Explanations

    assay, measurements, scientific terms

    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
    以任ä½ķ
    -0.08
    elas
    -0.08
    åħ±ãģ«
    -0.08
    лаго
    -0.08
    èĹIJ
    -0.08
    ebet
    -0.08
    ãģ¨ãĤĤãģ«
    -0.07
    askan
    -0.07
    inale
    -0.07
    adém
    -0.07
    POSITIVE LOGITS
    æĪĸéĢļè¿ĩ
    0.09
    æĪĸ缴æİ¥
    0.08
    çŃīæĸ¹å¼ı
    0.08
    æĪĸçĶ±
    0.08
    çŃīæīĭ段
    0.08
    çŃīæĸ¹æ³ķ
    0.07
    æīĭ段
    0.07
    æĪĸèĢħ缴æİ¥
    0.07
    uff
    0.07
    åħ³
    0.07
    Activations Density 0.393%

    No Known Activations