© 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. 17494
    Prev
    Next
    INDEX
    Explanations

    import android

    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
    ä½łå®¶
    -0.07
    edelta
    -0.06
    INUX
    -0.06
    etrie
    -0.06
     неÑĢаз
    -0.06
    лага
    -0.06
    enville
    -0.06
     tavo
    -0.06
    anders
    -0.06
     Moreno
    -0.06
    POSITIVE LOGITS
    throp
    0.07
    ages
    0.07
    uas
    0.07
    zkod
    0.07
    luck
    0.07
    .ly
    0.07
    论è¯ģ
    0.06
    ä¸Ģæ³¢
    0.06
    æĦıå¤ĸ伤害
    0.06
    .elapsed
    0.06
    Activations Density 0.034%

    No Known Activations