© 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. 62998
    Prev
    Next
    INDEX
    Explanations

    http links

    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
    grese
    -0.09
    kota
    -0.09
    hô
    -0.08
    Ñģнов
    -0.08
    ésil
    -0.08
    úi
    -0.08
    usercontent
    -0.08
    ADVERTISEMENT
    -0.08
    ´Ī
    -0.08
     handl
    -0.08
    POSITIVE LOGITS
    åħ·
    0.07
     fflush
    0.07
    -project
    0.07
    è¯Ŀ
    0.06
    -
    0.06
    æģ°
    0.06
     qual
    0.06
    åģļä¸ĢåIJį
    0.06
     cal
    0.06
    æĩĤ
    0.06
    Activations Density 0.777%

    No Known Activations