© 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. 34261
    Prev
    Next
    INDEX
    Explanations

    perfect, consequently, these

    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
    åĽŀäºĭ
    -0.09
     cotiz
    -0.07
     Rojas
    -0.07
    è¿Ļä¸ĢåĪĩ
    -0.07
    ernal
    -0.07
    úi
    -0.07
    Ậ
    -0.07
    æķ£å¸ĥ
    -0.07
    äºĨä¸ĢåĪĩ
    -0.07
    orial
    -0.07
    POSITIVE LOGITS
    ä¸įéĢĤçĶ¨
    0.08
    aven
    0.07
    å°¤åħ¶æĺ¯
    0.07
    å°¤åħ¶
    0.07
     especially
    0.07
     suitability
    0.07
     applicable
    0.07
    igh
    0.07
    ossa
    0.07
    éĤ£éĩĮçļĦ
    0.06
    Activations Density 0.256%

    No Known Activations