© 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. 2703
    Prev
    Next
    INDEX
    Explanations

    molecular weight (MW/Mr)

    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
    Ļ
    -0.07
    adeira
    -0.06
    æ±IJ
    -0.06
    æį¢æīĭ
    -0.06
    cean
    -0.06
    åľ¨éĩĮéĿ¢
    -0.06
    å¤ĩ
    -0.06
    кона
    -0.06
    æį¢ä¸Ģ个
    -0.06
    iggins
    -0.06
    POSITIVE LOGITS
    umus
    0.08
    大åħ³
    0.07
    endants
    0.07
    çĽ¸å¯¹åºĶçļĦ
    0.07
    对åºĶçļĦ
    0.07
    igar
    0.07
    ónde
    0.07
     corresponding
    0.07
    пл
    0.07
    ÙĤÙħ
    0.07
    Activations Density 0.017%

    No Known Activations