© 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. 21816
    Prev
    Next
    INDEX
    Explanations

    value or statement

    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
    çĭ±
    -0.08
    éķ¿ä¹IJ
    -0.07
    çīĪçļĦ
    -0.07
     anon
    -0.07
    _serial
    -0.07
    illery
    -0.07
    hev
    -0.07
     inilah
    -0.06
    ÙĪÙĦات
    -0.06
    åѤç«ĭ
    -0.06
    POSITIVE LOGITS
    achu
    0.07
    æĺĵçĪĨ
    0.07
    表çݰ为
    0.06
    ijin
    0.06
    ä¸Ģå¾ĭ
    0.06
    ADVERTISEMENT
    0.06
    é¢Ŀ为
    0.06
    ergen
    0.06
    ipi
    0.06
     boil
    0.06
    Activations Density 0.009%

    No Known Activations