© 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. 50432
    Prev
    Next
    INDEX
    Explanations

    there is/there's

    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
    æľīä»»ä½ķ
    -0.09
    ¾
    -0.09
    æľīæīĢ
    -0.08
    æľīå¤ļä¹Ī
    -0.08
     ëĮĢë¡ľ
    -0.08
    stration
    -0.08
    æľīä»Ģä¹Ī
    -0.08
    æŁIJæŁIJ
    -0.07
    sembled
    -0.07
    /testify
    -0.07
    POSITIVE LOGITS
    è¿ĺæľī个
    0.08
    éĢļ常ä¼ļ
    0.07
     gotta
    0.07
    anan
    0.07
    otti
    0.07
     ÑĤакже
    0.06
    hoven
    0.06
    è¿ĺæľīä¸Ģ个
    0.06
    neur
    0.06
    æĪIJäºĨä¸Ģ个
    0.06
    Activations Density 0.063%

    No Known Activations